# Upstash

Articles and tutorials on serverless technologies from Upstash and community.

This is one page of public article previews, not the complete archive. Follow Next page to continue. Summaries are not the original full articles.

## Redis for AI Agents: The Easiest Way for Agents to Share Memory

DevFeed: [Redis for AI Agents: The Easiest Way for Agents to Share Memory](<https://devfeed.tech/articles/redis-for-ai-agents-the-easiest-way-for-agents-to-share-memory-130786.md>)

Original publisher: [Read original article](<https://upstash.com/blog/upstash-for-agents>)

Author: Josh

Published: 2026-11-12T00:00:00Z

Content type: article

Language: en

Sources: [Upstash](<https://devfeed.tech/sources/upstash.md>)

Topics: [Redis](<https://devfeed.tech/topics/redis.md>), [Multi Agent Systems](<https://devfeed.tech/topics/multi-agent-systems.md>), [agent to agent communication](<https://devfeed.tech/topics/agent-to-agent-communication.md>)

Tags: [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-agents](<https://devfeed.tech/tags/ai-agents.md>), [api](<https://devfeed.tech/tags/api.md>), [cache](<https://devfeed.tech/tags/cache.md>), [crash](<https://devfeed.tech/tags/crash.md>), [database](<https://devfeed.tech/tags/database.md>), [file](<https://devfeed.tech/tags/file.md>), [free](<https://devfeed.tech/tags/free.md>), [job](<https://devfeed.tech/tags/job.md>), [lock](<https://devfeed.tech/tags/lock.md>), [mcp](<https://devfeed.tech/tags/mcp.md>), [memory](<https://devfeed.tech/tags/memory.md>), [queue](<https://devfeed.tech/tags/queue.md>), [redis](<https://devfeed.tech/tags/redis.md>), [share](<https://devfeed.tech/tags/share.md>)

### AI overview

The article shows how agents can share state through a free Upstash Redis database created with one HTTP request and an idempotency key; agents with its database ID can retrieve credentials and access the same data. Examples use a hash to resume work after a crash or context reset, a list as a queue that gives workers distinct jobs, expiring keys to lock files, and one-hour cache entries to avoid repeated API calls. The article notes that anyone with an unclaimed database ID can view, edit, or claim the database, so it recommends keeping the ID out of Git and storing no personal data or secrets there. Unclaimed databases expire after three days; claiming one moves it into an Upstash account with no expiry and the full free-tier quota. Usage metrics may lag by several minutes.

### Source excerpt

How AI agents use a free Upstash Redis database as shared memory: continue a task after a crash, split a job queue between sub-agents, lock a file, and cache slow API calls. With code and the output of each run.

## Give Hermes Agent a Long-Term Memory on Upstash Redis

DevFeed: [Give Hermes Agent a Long-Term Memory on Upstash Redis](<https://devfeed.tech/articles/give-hermes-agent-a-long-term-memory-on-upstash-redis-129331.md>)

Original publisher: [Read original article](<https://upstash.com/blog/hermes-agent-memory-upstash-redis>)

Author: Cahid Arda Oz

Published: 2026-11-06T00:00:00Z

Content type: article

Language: en

Sources: [Upstash](<https://devfeed.tech/sources/upstash.md>)

Topics: [hermes-agent](<https://devfeed.tech/topics/hermes-agent.md>), [Redis](<https://devfeed.tech/topics/redis.md>), [AI Context Management](<https://devfeed.tech/topics/ai-context-management.md>), [Retrieval Augmented Generation (RAG)](<https://devfeed.tech/topics/retrieval-augmented-generation-rag.md>)

Tags: [agent](<https://devfeed.tech/tags/agent.md>), [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [chat](<https://devfeed.tech/tags/chat.md>), [free](<https://devfeed.tech/tags/free.md>), [hermes](<https://devfeed.tech/tags/hermes.md>), [hermes-agent](<https://devfeed.tech/tags/hermes-agent.md>), [memory](<https://devfeed.tech/tags/memory.md>), [redis](<https://devfeed.tech/tags/redis.md>), [search](<https://devfeed.tech/tags/search.md>)

### AI overview

upstash-hermes-memory extends Hermes Agent's small built-in memory files by storing memories and session transcripts in Upstash Redis. Before each turn it uses hybrid search to add the three most related memories; after the turn it appends new messages to the transcript. Chat transcripts can be searched with fuzzy full-text matching, while Redis Search creates embeddings without a separate embedding model or vector database. Built-in memory remains active and is synchronized to Redis when facts are added, corrected, or removed. The integration uses one Redis Search index, so it can run on Upstash's Free plan; sharing the database with the TypeScript AgentKit integration requires a plan that allows more than one index. Setup requires a Redis REST URL and token, entered through `hermes memory setup` or configured manually after installing the Python package. The article says the main agent writes memory, while subagents, cron jobs, and context flushes can read it.

### Source excerpt

upstash-hermes-memory gives Hermes Agent long-term memory and searchable chat history on Upstash Redis. It recalls related memories on every turn and runs on the Free plan.

## Tuning Our MCP Server with Agent Benchmarks

DevFeed: [Tuning Our MCP Server with Agent Benchmarks](<https://devfeed.tech/articles/tuning-our-mcp-server-with-agent-benchmarks-116397.md>)

Original publisher: [Read original article](<https://upstash.com/blog/coding-agent-benchmark-mcp-server>)

Author: Cahid Arda Oz

Published: 2026-11-03T00:00:00Z

Content type: news

Language: en

Sources: [Upstash](<https://devfeed.tech/sources/upstash.md>)

Topics: [AI Agent](<https://devfeed.tech/topics/ai-agent.md>), [Benchmark](<https://devfeed.tech/topics/benchmark.md>), [Claude Code](<https://devfeed.tech/topics/claude-code.md>), [cursor](<https://devfeed.tech/topics/cursor.md>)

Tags: [agent](<https://devfeed.tech/tags/agent.md>), [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [benchmark](<https://devfeed.tech/tags/benchmark.md>), [benchmarks](<https://devfeed.tech/tags/benchmarks.md>), [coding](<https://devfeed.tech/tags/coding.md>), [coding-agents](<https://devfeed.tech/tags/coding-agents.md>), [fixed](<https://devfeed.tech/tags/fixed.md>), [mcp](<https://devfeed.tech/tags/mcp.md>), [mcp-server](<https://devfeed.tech/tags/mcp-server.md>), [redis](<https://devfeed.tech/tags/redis.md>), [results](<https://devfeed.tech/tags/results.md>), [tasks](<https://devfeed.tech/tags/tasks.md>)

### AI overview

A benchmark of 369 runs across seven coding agents found that most could complete Upstash Redis setup and rate-limiting tasks, but exposed four gaps: no daily-backup tool, confusion about Redis logs, delayed usage stats reported as zero, and deletes proceeding without confirmation. Upstash added a backup toggle, clarified log scope and an approximately two-minute stats delay, and made the first delete call non-destructive pending user confirmation. In reruns across five agent/model pairs, all answers to the weekly command-count question had been zero; afterward, four gave the right count and 11 reported that stats were still catching up. App setup and rate-limiting misses occurred only with Haiku 5.5; other tested models passed those tasks. Delete confirmation varied by agent, and the elicitation form required the person to type the database name.

### Source excerpt

We ran coding agents through real Upstash Redis tasks with the Upstash MCP server, fixed what the benchmark found, and compared the results before and after.

## How to Validate Token Audience in an MCP Server

DevFeed: [How to Validate Token Audience in an MCP Server](<https://devfeed.tech/articles/how-to-validate-token-audience-in-an-mcp-server-139489.md>)

Original publisher: [Read original article](<https://upstash.com/blog/mcp-oauth-token-audience>)

Author: Ramazan Onur Acar

Published: 2026-11-02T00:00:00Z

Content type: tutorial

Language: en

Sources: [Upstash](<https://devfeed.tech/sources/upstash.md>)

Topics: [Secure token management](<https://devfeed.tech/topics/secure-token-management.md>), [JSON Web Tokens](<https://devfeed.tech/topics/jwt.md>), [API Governance](<https://devfeed.tech/topics/api-governance.md>)

Tags: [2](<https://devfeed.tech/tags/2.md>), [2025](<https://devfeed.tech/tags/2025.md>), [2026](<https://devfeed.tech/tags/2026.md>), [3](<https://devfeed.tech/tags/3.md>), [about](<https://devfeed.tech/tags/about.md>), [authorization](<https://devfeed.tech/tags/authorization.md>), [avoid](<https://devfeed.tech/tags/avoid.md>), [context7](<https://devfeed.tech/tags/context7.md>), [guide](<https://devfeed.tech/tags/guide.md>), [log](<https://devfeed.tech/tags/log.md>), [mcp](<https://devfeed.tech/tags/mcp.md>), [mcp-server](<https://devfeed.tech/tags/mcp-server.md>), [oauth](<https://devfeed.tech/tags/oauth.md>), [parameter](<https://devfeed.tech/tags/parameter.md>), [problems](<https://devfeed.tech/tags/problems.md>), [resource](<https://devfeed.tech/tags/resource.md>), [rules](<https://devfeed.tech/tags/rules.md>), [security](<https://devfeed.tech/tags/security.md>), [send](<https://devfeed.tech/tags/send.md>), [server](<https://devfeed.tech/tags/server.md>), [spec](<https://devfeed.tech/tags/spec.md>), [token](<https://devfeed.tech/tags/token.md>), [users](<https://devfeed.tech/tags/users.md>)

### AI overview

The MCP authorization spec requires clients to identify the target server with `resource` and servers to reject tokens intended for another audience. The guide recommends locally verifying signed JWT access tokens, including `aud`, the `at+jwt` type, and an allowed signing algorithm; configure the authorization server to copy `resource` into `aud`. Roll out enforcement by logging mismatches, rejecting other servers' tokens, then rejecting tokens without an audience by a chosen date. During outages, return 503 when token validity cannot be determined, reserving 401 for known-invalid tokens. The excerpt also covers sign-in requests missing `resource`, legacy refresh tokens without `aud`, canonical server URLs, gateway-issued tokens, and avoiding forwarding client tokens to downstream APIs. Clients should send the same `resource` at sign-in, token request, and refresh.

### Source excerpt

A short guide to the audience rules in the MCP authorization spec. Send the resource parameter, put it in the token's aud claim, check it in your MCP server, and avoid the problems that log users out.

## Step-level flow control and retries in Upstash Workflow

DevFeed: [Step-level flow control and retries in Upstash Workflow](<https://devfeed.tech/articles/step-level-flow-control-and-retries-in-upstash-workflow-105962.md>)

Original publisher: [Read original article](<https://upstash.com/blog/step-level-flow-control-and-retries-in-upstash-workflow>)

Author: Cahid Arda Oz

Published: 2026-10-28T00:00:00Z

Content type: release

Language: en

Sources: [Upstash](<https://devfeed.tech/sources/upstash.md>)

Topics: [workflow automation](<https://devfeed.tech/topics/workflow-automation.md>), [Distributed Systems & Parallel Computing](<https://devfeed.tech/topics/distributed-systems-parallel-computing.md>)

Tags: [api](<https://devfeed.tech/tags/api.md>), [context](<https://devfeed.tech/tags/context.md>), [flow-control](<https://devfeed.tech/tags/flow-control.md>), [parallelism](<https://devfeed.tech/tags/parallelism.md>), [payment](<https://devfeed.tech/tags/payment.md>), [qstash](<https://devfeed.tech/tags/qstash.md>), [retries](<https://devfeed.tech/tags/retries.md>), [run](<https://devfeed.tech/tags/run.md>), [workflow](<https://devfeed.tech/tags/workflow.md>)

### AI overview

Upstash Workflow lets you override flow control and retry settings for an individual step by passing a third argument to `context.run`. This is useful when one step, such as a payment API call, needs stricter concurrency limits or more retries than the rest of the workflow. The step's flow control overrides the run-level limits for that step and does not count toward them; a shared flow control key can limit matching steps across runs. Unspecified retry fields default to the run's configuration. You can combine `flowControl`, `retries`, and `retryDelay`, and inspect the effective settings for each step in the QStash workflow logs.

### Source excerpt

Upstash Workflow now lets you set flow control and retries on a single step with the third argument of context.run, instead of applying them to the whole run.

## Context7 vs Exa 3.0 on WebCode: The Same Accuracy in a Fifth of the Tokens

DevFeed: [Context7 vs Exa 3.0 on WebCode: The Same Accuracy in a Fifth of the Tokens](<https://devfeed.tech/articles/context7-vs-exa-3-0-on-webcode-the-same-accuracy-in-a-fifth-of-the-tokens-103671.md>)

Original publisher: [Read original article](<https://upstash.com/blog/context7-search-webcode>)

Author: Ramazan Onur Acar

Published: 2026-10-27T00:00:00Z

Content type: news

Language: en

Sources: [Upstash](<https://devfeed.tech/sources/upstash.md>)

Topics: [Benchmark](<https://devfeed.tech/topics/benchmark.md>), [code search](<https://devfeed.tech/topics/code-search.md>), [Machine learning](<https://devfeed.tech/topics/machine-learning.md>), [Claude](<https://devfeed.tech/topics/claude.md>)

Tags: [adapter](<https://devfeed.tech/tags/adapter.md>), [agent](<https://devfeed.tech/tags/agent.md>), [agents](<https://devfeed.tech/tags/agents.md>), [api](<https://devfeed.tech/tags/api.md>), [api-key](<https://devfeed.tech/tags/api-key.md>), [bazel](<https://devfeed.tech/tags/bazel.md>), [benchmark](<https://devfeed.tech/tags/benchmark.md>), [browser](<https://devfeed.tech/tags/browser.md>), [claude](<https://devfeed.tech/tags/claude.md>), [claude-opus](<https://devfeed.tech/tags/claude-opus.md>), [claude-opus-5-5](<https://devfeed.tech/tags/claude-opus-5-5.md>), [client](<https://devfeed.tech/tags/client.md>), [code](<https://devfeed.tech/tags/code.md>), [coding](<https://devfeed.tech/tags/coding.md>), [coding-agents](<https://devfeed.tech/tags/coding-agents.md>), [compute](<https://devfeed.tech/tags/compute.md>), [context7](<https://devfeed.tech/tags/context7.md>), [curl](<https://devfeed.tech/tags/curl.md>), [search](<https://devfeed.tech/tags/search.md>), [tokens](<https://devfeed.tech/tags/tokens.md>)

### AI overview

In the 307-question WebCode RAG benchmark, Context7 Search and Exa 3.0 produced similar correct-answer rates: 85.7% for Context7 and 86.2% for Exa Lite and Auto. With the same answer and judge models, Context7 responses averaged about 1,050 tokens and led to fewer wrong answers (2.3%, versus 7.3% for Lite and 8.0% for Auto); Exa searches were faster, at 0.6 seconds for Lite and 1.3 for Auto versus 3.7 for Context7. The authors attribute the wrong-answer gap to Context7 results being shorter and more likely to contain the answer, and to the model more often declining when they did not. Results are averages across three production runs; the authors build Context7, and the comparison covers this benchmark and configuration.

### Source excerpt

On Exa's WebCode benchmark, Context7 Search and Exa 3.0 led to as many correct answers, with about a fifth of the tokens for Context7 and a third of the wrong answers.

## Better than Grok Bot: Running Customer Success with Hermes on Upstash Box

DevFeed: [Better than Grok Bot: Running Customer Success with Hermes on Upstash Box](<https://devfeed.tech/articles/better-than-grok-bot-running-customer-success-with-hermes-on-upstash-box-101491.md>)

Original publisher: [Read original article](<https://upstash.com/blog/hermes-on-upstash-box-customer-success>)

Author: Sertuğ Kaya

Published: 2026-10-26T00:00:00Z

Content type: article

Language: en

Sources: [Upstash](<https://devfeed.tech/sources/upstash.md>)

Topics: [hermes-agent](<https://devfeed.tech/topics/hermes-agent.md>), [Open Source](<https://devfeed.tech/topics/open-source.md>), [Agent Skills](<https://devfeed.tech/topics/agent-skills.md>), [AI for customer service automation](<https://devfeed.tech/topics/ai-for-customer-service-automation.md>), [AI Infrastructure](<https://devfeed.tech/topics/ai-infrastructure.md>), [AI Chat](<https://devfeed.tech/topics/ai-chat.md>), [Bot](<https://devfeed.tech/topics/bot.md>)

Tags: [agent](<https://devfeed.tech/tags/agent.md>), [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [always-on-assistant](<https://devfeed.tech/tags/always-on-assistant.md>), [app](<https://devfeed.tech/tags/app.md>), [apps](<https://devfeed.tech/tags/apps.md>), [automated](<https://devfeed.tech/tags/automated.md>), [background](<https://devfeed.tech/tags/background.md>), [billing](<https://devfeed.tech/tags/billing.md>), [board](<https://devfeed.tech/tags/board.md>), [box](<https://devfeed.tech/tags/box.md>), [browser](<https://devfeed.tech/tags/browser.md>), [build](<https://devfeed.tech/tags/build.md>), [customer](<https://devfeed.tech/tags/customer.md>), [customer-success](<https://devfeed.tech/tags/customer-success.md>), [grok-bot](<https://devfeed.tech/tags/grok-bot.md>), [hermes](<https://devfeed.tech/tags/hermes.md>), [lean](<https://devfeed.tech/tags/lean.md>), [mcp](<https://devfeed.tech/tags/mcp.md>), [nous-research](<https://devfeed.tech/tags/nous-research.md>), [open-source](<https://devfeed.tech/tags/open-source.md>), [open-source-agent](<https://devfeed.tech/tags/open-source-agent.md>)

### AI overview

The author runs Hermes, Nous Research's open-source agent, on an always-on Upstash Box so scheduled briefs and meeting preparation continue while their laptop sleeps. Slack on mobile and Hermes Desktop share the same agent and memory; Upsy connects it to work apps and provides a cloud browser. Hermes monitors customer and account signals, prepares call briefs, triages email, and drafts outreach, while the author retains approval over sending messages or changing plans and billing. The author reports that a Small Box was sufficient for the setup's observed usage, with Medium suggested as a growth buffer, and describes using temporary Boxes for heavier jobs. Setup guidance includes completing Upsy sign-in through a local browser when the Box has no browser, limiting the Upstash MCP account to a sandbox because access covers all products in it, and writing explicit approval rules.

### Source excerpt

How I run Customer Success at a lean startup with Hermes, the open-source agent from Nous Research, living on an always-on Upstash Box and connected to my work apps through Upsy.

## How Upsy Uses MCP Tasks to Keep Agents in a Meeting

DevFeed: [How Upsy Uses MCP Tasks to Keep Agents in a Meeting](<https://devfeed.tech/articles/how-upsy-uses-mcp-tasks-to-keep-agents-in-a-meeting-98985.md>)

Original publisher: [Read original article](<https://upstash.com/blog/upsy-mcp-tasks>)

Author: Enes Akar

Published: 2026-10-24T00:00:00Z

Content type: article

Language: en

Sources: [Upstash](<https://devfeed.tech/sources/upstash.md>)

Topics: [Multi Agent Systems](<https://devfeed.tech/topics/multi-agent-systems.md>), [async](<https://devfeed.tech/topics/async.md>), [agentic workflows](<https://devfeed.tech/topics/agentic-workflows.md>)

Tags: [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [mcp](<https://devfeed.tech/tags/mcp.md>), [redis](<https://devfeed.tech/tags/redis.md>), [tasks](<https://devfeed.tech/tags/tasks.md>)

### AI overview

Upsy Meet uses MCP Tasks to let supported Claude Code clients wait for meeting messages without blocking their work or generating repeated model turns. Instead of starting a background job, each `tasks/get` checks Redis for messages since the agent's last read; the task stores only the wait state. Upsy allows one wait per seat, skips the agent's own messages, returns immediately when messages already exist, and increases polling intervals from 2 to 30 seconds as a meeting goes quiet. `tasks/get` requests use a lighter server path but still undergo token checks. Clients that do not declare Tasks support continue using the existing 50-second `meeting_wait` polling loop. The article reports that Tasks require Claude Code CLI v2.1.304 or later and that the TypeScript SDK must be v2.3.1 or later for the extension's `tasks/get` and `tasks/cancel` handlers to work.

### Source excerpt

Upsy Meet is a meeting room for AI agents. Here's how we use the MCP Tasks extension so Claude Code can listen in a meeting without polling, with nothing but Redis behind it.

## MCP Tasks and Elicitations in Claude Code: Long-Running Tools That Can Ask You Things

DevFeed: [MCP Tasks and Elicitations in Claude Code: Long-Running Tools That Can Ask You Things](<https://devfeed.tech/articles/mcp-tasks-and-elicitations-in-claude-code-long-running-tools-that-can-ask-you-things-98554.md>)

Original publisher: [Read original article](<https://upstash.com/blog/claude-code-mcp-tasks>)

Author: Cahid Arda Oz

Published: 2026-10-23T00:00:00Z

Content type: tutorial

Language: en

Sources: [Upstash](<https://devfeed.tech/sources/upstash.md>)

Topics: [MSP MCP](<https://devfeed.tech/topics/msp-mcp.md>), [Serverless](<https://devfeed.tech/topics/serverless.md>), [Claude Code](<https://devfeed.tech/topics/claude-code.md>), [anthropic](<https://devfeed.tech/topics/anthropic.md>)

Tags: [2026](<https://devfeed.tech/tags/2026.md>), [actions](<https://devfeed.tech/tags/actions.md>), [agent](<https://devfeed.tech/tags/agent.md>), [agent-sdk](<https://devfeed.tech/tags/agent-sdk.md>), [agentkit](<https://devfeed.tech/tags/agentkit.md>), [agents](<https://devfeed.tech/tags/agents.md>), [agntcon](<https://devfeed.tech/tags/agntcon.md>), [ai](<https://devfeed.tech/tags/ai.md>), [beta](<https://devfeed.tech/tags/beta.md>), [claude-code](<https://devfeed.tech/tags/claude-code.md>), [cli](<https://devfeed.tech/tags/cli.md>), [client](<https://devfeed.tech/tags/client.md>), [clients](<https://devfeed.tech/tags/clients.md>), [complete](<https://devfeed.tech/tags/complete.md>), [deploy](<https://devfeed.tech/tags/deploy.md>), [desktop](<https://devfeed.tech/tags/desktop.md>), [desktop-app](<https://devfeed.tech/tags/desktop-app.md>), [long-running](<https://devfeed.tech/tags/long-running.md>), [mcp](<https://devfeed.tech/tags/mcp.md>), [qstash](<https://devfeed.tech/tags/qstash.md>), [serverless](<https://devfeed.tech/tags/serverless.md>), [tasks](<https://devfeed.tech/tags/tasks.md>), [tools](<https://devfeed.tech/tags/tools.md>)

### AI overview

MCP Tasks let supported clients return a task handle promptly, poll for completion, and optionally cancel; Elicitations let a server ask the user a structured question and continue after a response. The excerpt says Claude Code CLI supports both in interactive terminal sessions, Agent SDK sessions, and GitHub Actions, while subagent calls, one-shot `claude -p`, the VS Code extension, and desktop app do not use native Tasks; questions reach the user only in interactive terminal sessions. `@upstash/mcp-toolkit/tasks` can provide native Tasks to capable clients and task-status/cancel tools to others. For serverless use, Redis stores tasks across invocations and QStash dispatches execution with retries; longer work can use `WorkflowDispatcher`, which runs steps in separate invocations and can wait for an elicitation answer without occupying a function. The excerpt says `QStashDispatcher` runs a task in one invocation and cannot wait for an answer. In-memory tasks can disappear on restart or be unavailable across instances.

### Source excerpt

Articles and tutorials on serverless technologies from Upstash and community

## What Are MCP Apps? The Upstash Console Inside ChatGPT

DevFeed: [What Are MCP Apps? The Upstash Console Inside ChatGPT](<https://devfeed.tech/articles/what-are-mcp-apps-the-upstash-console-inside-chatgpt-93074.md>)

Original publisher: [Read original article](<https://upstash.com/blog/mcp-apps-upstash-console>)

Author: Cahid Arda Oz

Published: 2026-10-21T00:00:00Z

Content type: article

Language: en

Sources: [Upstash](<https://devfeed.tech/sources/upstash.md>)

Topics: [MSP MCP](<https://devfeed.tech/topics/msp-mcp.md>), [Interaction Design](<https://devfeed.tech/topics/interaction-design.md>), [ChatGPT](<https://devfeed.tech/topics/chatgpt.md>), [console](<https://devfeed.tech/topics/console.md>)

Tags: [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [chatgpt](<https://devfeed.tech/tags/chatgpt.md>), [console](<https://devfeed.tech/tags/console.md>), [database-performance](<https://devfeed.tech/tags/database-performance.md>), [mcp](<https://devfeed.tech/tags/mcp.md>), [mcp-apps](<https://devfeed.tech/tags/mcp-apps.md>), [redis](<https://devfeed.tech/tags/redis.md>)

### AI overview

MCP Apps let an MCP server pair a tool with an interactive HTML page that a compatible host renders in a sandboxed iframe. The host mediates page requests to server tools and can ask the user to confirm; the page can reuse the connection already authorized for the agent. Hosts without MCP Apps support still get the server's usual tools. Upstash says its MCP server serves a console inside ChatGPT, using the same layout as its web console. The page holds no credentials: reads and writes go through ChatGPT using the same OAuth grant as the agent, and read-only access hides write controls. Database tokens are fetched only when requested and are not sent to the model. The server also offers Redis Insights data through tools and a console tab; Insights is part of Prod Pack.

### Source excerpt

What an MCP App is, how hosts render one, and how the Upstash console runs as an MCP App in ChatGPT.

## Get Started with AI Agent Sandboxes for Free on Upstash Box

DevFeed: [Get Started with AI Agent Sandboxes for Free on Upstash Box](<https://devfeed.tech/articles/get-started-with-ai-agent-sandboxes-for-free-on-upstash-box-90279.md>)

Original publisher: [Read original article](<https://upstash.com/blog/getting-started-with-ai-agent-sandboxes-for-free>)

Author: Ali Tarık Şahin

Published: 2026-10-19T00:00:00Z

Content type: tutorial

Language: en

Sources: [Upstash](<https://devfeed.tech/sources/upstash.md>)

Topics: [AI Sandbox](<https://devfeed.tech/topics/ai-sandbox.md>), [Claude Code](<https://devfeed.tech/topics/claude-code.md>), [Node.js](<https://devfeed.tech/topics/node-js.md>)

Tags: [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [box](<https://devfeed.tech/tags/box.md>), [claude-code](<https://devfeed.tech/tags/claude-code.md>), [run](<https://devfeed.tech/tags/run.md>), [sandbox](<https://devfeed.tech/tags/sandbox.md>), [sandboxes](<https://devfeed.tech/tags/sandboxes.md>), [typescript](<https://devfeed.tech/tags/typescript.md>)

### AI overview

A hands-on guide to using Upstash Box's free tier to create isolated sandboxes for generated code and coding agents. It covers TypeScript setup, running commands and code, starting Claude Code, and pausing, snapshotting, and deleting boxes. It also explains limits on secrets and network access and outlines when paid plans may be needed.

### Source excerpt

Set up an AI agent sandbox on Upstash Box's free tier. Run generated code and Claude Code, manage files, and save snapshots with the TypeScript SDK.

## How to Run Coding Agents in Parallel in the Cloud (2026)

DevFeed: [How to Run Coding Agents in Parallel in the Cloud (2026)](<https://devfeed.tech/articles/how-to-run-coding-agents-in-parallel-in-the-cloud-2026-88071.md>)

Original publisher: [Read original article](<https://upstash.com/blog/run-coding-agents-in-parallel-with-upstash-box>)

Author: Ali Tarık Şahin

Published: 2026-10-15T00:00:00Z

Content type: tutorial

Language: en

Sources: [Upstash](<https://devfeed.tech/sources/upstash.md>)

Topics: [Docker Sandboxes](<https://devfeed.tech/topics/docker-sandboxes.md>), [AI-assisted coding](<https://devfeed.tech/topics/ai-assisted-coding.md>), [parallel workspaces](<https://devfeed.tech/topics/parallel-workspaces.md>), [AI Sandbox](<https://devfeed.tech/topics/ai-sandbox.md>)

Tags: [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [box](<https://devfeed.tech/tags/box.md>), [coding-agents](<https://devfeed.tech/tags/coding-agents.md>), [parallel](<https://devfeed.tech/tags/parallel.md>), [sandbox](<https://devfeed.tech/tags/sandbox.md>), [snapshot](<https://devfeed.tech/tags/snapshot.md>), [tests](<https://devfeed.tech/tags/tests.md>)

### AI overview

The article explains how to run coding agents in parallel with Upstash Box by preparing and snapshotting a repository, launching an isolated box for each task, testing and reviewing each agent's patch, and cleaning up the boxes. It also discusses acceptance checks, pull requests, merge conflicts, security limits, pricing, and alternatives.

### Source excerpt

Run coding agents in parallel with Upstash Box. Clone once, snapshot the repo, and give each agent an isolated sandbox for tests, patches, and PRs.

## How to Build Your Own Lovable: An AI App Builder on Upstash Box

DevFeed: [How to Build Your Own Lovable: An AI App Builder on Upstash Box](<https://devfeed.tech/articles/how-to-build-your-own-lovable-an-ai-app-builder-on-upstash-box-88070.md>)

Original publisher: [Read original article](<https://upstash.com/blog/build-your-own-lovable>)

Author: Ali Tarık Şahin

Published: 2026-10-15T00:00:00Z

Content type: tutorial

Language: en

Sources: [Upstash](<https://devfeed.tech/sources/upstash.md>)

Topics: [app builder](<https://devfeed.tech/topics/app-builder.md>), [Claude Code](<https://devfeed.tech/topics/claude-code.md>)

Tags: [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-app-builder](<https://devfeed.tech/tags/ai-app-builder.md>), [box](<https://devfeed.tech/tags/box.md>), [change](<https://devfeed.tech/tags/change.md>), [claude-code](<https://devfeed.tech/tags/claude-code.md>), [coding-agent](<https://devfeed.tech/tags/coding-agent.md>), [comparison](<https://devfeed.tech/tags/comparison.md>), [sandbox](<https://devfeed.tech/tags/sandbox.md>)

### AI overview

A hands-on guide to building a Lovable-style AI app builder with one Upstash Box per project. It describes the coding agent, live preview, saved versions and forks, and reports setup timings and usage costs from test runs.

### Source excerpt

Build a Lovable-style AI app builder with a coding agent, live preview, versions, and forks. One Upstash Box per project, with real timings and costs.

## Cloud Computers for AI Agents: How to Give an AI Agent Its Own Computer (2026)

DevFeed: [Cloud Computers for AI Agents: How to Give an AI Agent Its Own Computer (2026)](<https://devfeed.tech/articles/cloud-computers-for-ai-agents-how-to-give-an-ai-agent-its-own-computer-2026-87118.md>)

Original publisher: [Read original article](<https://upstash.com/blog/cloud-computer-for-ai-agents>)

Author: Ali Tarık Şahin

Published: 2026-10-14T00:00:00Z

Content type: tutorial

Language: en

Sources: [Upstash](<https://devfeed.tech/sources/upstash.md>)

Topics: [Cloud](<https://devfeed.tech/topics/cloud.md>), [AI Agent](<https://devfeed.tech/topics/ai-agent.md>), [agent orchestration](<https://devfeed.tech/topics/agent-orchestration.md>), [virtual machines](<https://devfeed.tech/topics/virtual-machines.md>)

Tags: [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [automation](<https://devfeed.tech/tags/automation.md>), [aws](<https://devfeed.tech/tags/aws.md>), [box](<https://devfeed.tech/tags/box.md>), [built-in](<https://devfeed.tech/tags/built-in.md>), [cloud](<https://devfeed.tech/tags/cloud.md>), [codex](<https://devfeed.tech/tags/codex.md>), [coding](<https://devfeed.tech/tags/coding.md>), [computer](<https://devfeed.tech/tags/computer.md>), [configuration](<https://devfeed.tech/tags/configuration.md>), [container](<https://devfeed.tech/tags/container.md>), [how-to](<https://devfeed.tech/tags/how-to.md>), [sandbox](<https://devfeed.tech/tags/sandbox.md>)

### AI overview

The article explains how to provide AI agents with cloud computers, comparing plain virtual machines, desktop sandboxes, and agent-focused persistent environments. It walks through creating an Upstash Box for a user, running coding tasks, checking results in a browser, saving snapshots, pausing and resuming work, and choosing scheduled or always-on operation. It also describes pricing and isolation features, along with limitations such as container-based isolation, AWS us-east-1 availability, no GPU support, and planned custom Docker images.

### Source excerpt

How to give an AI agent its own computer in the cloud: what it needs, the three ways to get one, and a full walkthrough of a persistent agent workspace that you create, put to work, save, pause and come back to the next day.

## Backblaze B2 Pricing Explained (October 2026): Storage, Egress and API Costs vs. Upstash Blob

DevFeed: [Backblaze B2 Pricing Explained (October 2026): Storage, Egress and API Costs vs. Upstash Blob](<https://devfeed.tech/articles/backblaze-b2-pricing-explained-october-2026-storage-egress-and-api-costs-vs-upstash-blob-85775.md>)

Original publisher: [Read original article](<https://upstash.com/blog/backblaze-b2-pricing-explained-2026>)

Author: Josh

Published: 2026-10-12T00:00:00Z

Content type: comparison

Language: en

Sources: [Upstash](<https://devfeed.tech/sources/upstash.md>)

Topics: [Magic Pocket](<https://devfeed.tech/topics/magic-pocket.md>), [Cloudflare](<https://devfeed.tech/topics/cloudflare.md>), [API](<https://devfeed.tech/topics/api.md>)

Tags: [aws-s3](<https://devfeed.tech/tags/aws-s3.md>), [aws-sdk](<https://devfeed.tech/tags/aws-sdk.md>), [blob](<https://devfeed.tech/tags/blob.md>), [cloudflare](<https://devfeed.tech/tags/cloudflare.md>), [cors](<https://devfeed.tech/tags/cors.md>), [costs](<https://devfeed.tech/tags/costs.md>), [deploy](<https://devfeed.tech/tags/deploy.md>), [egress](<https://devfeed.tech/tags/egress.md>), [pricing](<https://devfeed.tech/tags/pricing.md>), [storage](<https://devfeed.tech/tags/storage.md>)

### AI overview

Backblaze B2 charges $6.95 per TB per month and includes downloads up to three times the average stored data, with additional egress billed at $0.01 per GB. The article compares those costs and setup requirements with Upstash Blob for applications serving files, including CDN delivery, signed URLs, and browser uploads.

### Source excerpt

Backblaze B2 costs $6.95 per TB a month, with free downloads up to 3x what you store. Here is every line on a B2 bill, and when Upstash Blob's 1 TB of free downloads costs less for app files.

## What Your Search Tool Sends Your Coding Agent

DevFeed: [What Your Search Tool Sends Your Coding Agent](<https://devfeed.tech/articles/what-your-search-tool-sends-your-coding-agent-85776.md>)

Original publisher: [Read original article](<https://upstash.com/blog/what-search-hands-your-agent>)

Author: Ramazan Onur Acar

Published: 2026-10-11T00:00:00Z

Content type: article

Language: en

Sources: [Upstash](<https://devfeed.tech/sources/upstash.md>)

Topics: [devrig](<https://devfeed.tech/topics/devrig.md>), [ecosystem-security](<https://devfeed.tech/topics/ecosystem-security.md>), [AI Agent](<https://devfeed.tech/topics/ai-agent.md>), [DuckDuckGo](<https://devfeed.tech/topics/duckduckgo.md>), [Algolia](<https://devfeed.tech/topics/algolia.md>)

Tags: [account-takeover](<https://devfeed.tech/tags/account-takeover.md>), [ai](<https://devfeed.tech/tags/ai.md>), [api](<https://devfeed.tech/tags/api.md>), [attacks](<https://devfeed.tech/tags/attacks.md>), [backdoor](<https://devfeed.tech/tags/backdoor.md>), [brave](<https://devfeed.tech/tags/brave.md>), [claude-code](<https://devfeed.tech/tags/claude-code.md>), [code](<https://devfeed.tech/tags/code.md>), [codex](<https://devfeed.tech/tags/codex.md>), [coding-agent](<https://devfeed.tech/tags/coding-agent.md>), [coding-agents](<https://devfeed.tech/tags/coding-agents.md>), [context7](<https://devfeed.tech/tags/context7.md>), [cursor](<https://devfeed.tech/tags/cursor.md>), [fake](<https://devfeed.tech/tags/fake.md>), [firecrawl](<https://devfeed.tech/tags/firecrawl.md>), [security](<https://devfeed.tech/tags/security.md>)

### AI overview

The article compares how six search tools return potentially dangerous documentation to coding agents, then tests whether language models repeat those instructions. Search tools that return full page bodies often included risky passages, while Context7 returned fewer; when harmful passages reached models through web search, they were passed along in 35% of cases. The authors caution that the study used nine known pages and does not establish rates across the web or shipped assistants.

### Source excerpt

Most dangerous docs aren't attacks. They're honest pages telling your agent to fetch something unpinned and run it. We measured how often six search tools pass them on.

## Grok Bot vs Muse vs OpenClaw vs Hermes: Personal AI Assistants Compared (2026)

DevFeed: [Grok Bot vs Muse vs OpenClaw vs Hermes: Personal AI Assistants Compared (2026)](<https://devfeed.tech/articles/grok-bot-vs-muse-vs-openclaw-vs-hermes-personal-ai-assistants-compared-2026-84266.md>)

Original publisher: [Read original article](<https://upstash.com/blog/grok-bot-vs-muse-vs-openclaw-vs-hermes>)

Author: Ali Tarık Şahin

Published: 2026-10-09T00:00:00Z

Content type: comparison

Language: en

Sources: [Upstash](<https://devfeed.tech/sources/upstash.md>)

Topics: [OpenClaw](<https://devfeed.tech/topics/openclaw.md>), [hermes-agent](<https://devfeed.tech/topics/hermes-agent.md>), [AI connector platforms](<https://devfeed.tech/topics/ai-connector-platforms.md>), [AI Context Management](<https://devfeed.tech/topics/ai-context-management.md>), [AI Chat](<https://devfeed.tech/topics/ai-chat.md>)

Tags: [agent](<https://devfeed.tech/tags/agent.md>), [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-assistants](<https://devfeed.tech/tags/ai-assistants.md>), [api](<https://devfeed.tech/tags/api.md>), [box](<https://devfeed.tech/tags/box.md>), [cloud-sandboxes](<https://devfeed.tech/tags/cloud-sandboxes.md>), [comparison](<https://devfeed.tech/tags/comparison.md>), [connectors](<https://devfeed.tech/tags/connectors.md>), [daytona](<https://devfeed.tech/tags/daytona.md>), [docker](<https://devfeed.tech/tags/docker.md>), [mcp](<https://devfeed.tech/tags/mcp.md>)

### AI overview

This comparison examines four personal AI assistants: hosted services Grok Bot and Meta Muse, and self-hosted open-source projects OpenClaw and Hermes. It contrasts their features, model and data controls, security considerations, costs, and hosting options to help readers choose based on their needs.

### Source excerpt

A simple comparison of four personal AI assistants in 2026: Grok Bot, Meta Muse, OpenClaw and Hermes. What each one does well, what it costs, and where it runs.

## AWS S3 Pricing Explained (2026): Storage, Requests and Data Transfer Costs

DevFeed: [AWS S3 Pricing Explained (2026): Storage, Requests and Data Transfer Costs](<https://devfeed.tech/articles/aws-s3-pricing-explained-2026-storage-requests-and-data-transfer-costs-84265.md>)

Original publisher: [Read original article](<https://upstash.com/blog/aws-s3-pricing-explained-2026>)

Author: Josh

Published: 2026-10-09T00:00:00Z

Content type: article

Language: en

Sources: [Upstash](<https://devfeed.tech/sources/upstash.md>)

Topics: [Amazon S3](<https://devfeed.tech/topics/amazon-s3.md>), [AWS Local Zones](<https://devfeed.tech/topics/aws-local-zones.md>), [cURL](<https://devfeed.tech/topics/curl.md>)

Tags: [analytics](<https://devfeed.tech/tags/analytics.md>), [aws](<https://devfeed.tech/tags/aws.md>), [aws-s3](<https://devfeed.tech/tags/aws-s3.md>), [blob](<https://devfeed.tech/tags/blob.md>), [cloudfront](<https://devfeed.tech/tags/cloudfront.md>), [costs](<https://devfeed.tech/tags/costs.md>), [pricing](<https://devfeed.tech/tags/pricing.md>), [s3](<https://devfeed.tech/tags/s3.md>), [storage](<https://devfeed.tech/tags/storage.md>)

### AI overview

An explanation of Amazon S3 pricing covering storage classes, minimum size and duration charges, requests, data transfer, CloudFront, and additional fees. It provides a method and script for estimating application bills and compares example costs with Upstash Blob.

### Source excerpt

AWS S3 pricing for 2026: storage classes, request and data transfer rates, CloudFront plans, the minimums that raise a bill, and worked examples.

## MCP Tasks and Events, Explained: Long-Running Tools and Agents That Wake Up

DevFeed: [MCP Tasks and Events, Explained: Long-Running Tools and Agents That Wake Up](<https://devfeed.tech/articles/mcp-tasks-and-events-explained-long-running-tools-and-agents-that-wake-up-78688.md>)

Original publisher: [Read original article](<https://upstash.com/blog/mcp-tasks-and-events>)

Author: Cahid Arda Oz

Published: 2026-10-09T00:00:00Z

Content type: tutorial

Language: en

Sources: [Upstash](<https://devfeed.tech/sources/upstash.md>)

Topics: [MSP MCP](<https://devfeed.tech/topics/msp-mcp.md>), [long-running](<https://devfeed.tech/topics/long-running.md>), [agentic-coding](<https://devfeed.tech/topics/agentic-coding.md>)

Tags: [agents](<https://devfeed.tech/tags/agents.md>), [events](<https://devfeed.tech/tags/events.md>), [long-running](<https://devfeed.tech/tags/long-running.md>), [mcp](<https://devfeed.tech/tags/mcp.md>), [qstash](<https://devfeed.tech/tags/qstash.md>), [redis](<https://devfeed.tech/tags/redis.md>), [serverless](<https://devfeed.tech/tags/serverless.md>), [servers](<https://devfeed.tech/tags/servers.md>), [webhook](<https://devfeed.tech/tags/webhook.md>)

### AI overview

The article explains MCP Tasks for long-running work and the proposed MCP Events design for waking agents when watched events occur. It describes current support and shows how @upstash/mcp-toolkit implements durable tasks and webhook events using Redis, QStash, and Upstash Workflow, with examples tested in ChatGPT.

### Source excerpt

How the MCP Tasks extension and the proposed MCP Events design work, which clients and servers support them today, and how @upstash/mcp-toolkit gives you durable long-running tools and webhook events now.

## I Gave Grok Bot a Remote Computer

DevFeed: [I Gave Grok Bot a Remote Computer](<https://devfeed.tech/articles/i-gave-grok-bot-a-remote-computer-78686.md>)

Original publisher: [Read original article](<https://upstash.com/blog/i-gave-grok-bot-a-remote-computer>)

Author: Ali Tarık Şahin

Published: 2026-10-07T00:00:00Z

Content type: article

Language: en

Sources: [Upstash](<https://devfeed.tech/sources/upstash.md>)

Topics: [remote-development](<https://devfeed.tech/topics/remote-development.md>), [MSP MCP](<https://devfeed.tech/topics/msp-mcp.md>), [Bot](<https://devfeed.tech/topics/bot.md>)

Tags: [agent-workflows](<https://devfeed.tech/tags/agent-workflows.md>), [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-assistants](<https://devfeed.tech/tags/ai-assistants.md>), [blob](<https://devfeed.tech/tags/blob.md>), [box](<https://devfeed.tech/tags/box.md>), [github](<https://devfeed.tech/tags/github.md>), [grok-bot](<https://devfeed.tech/tags/grok-bot.md>), [mcp](<https://devfeed.tech/tags/mcp.md>), [remote](<https://devfeed.tech/tags/remote.md>)

### AI overview

The author connects Grok Bot to an Upstash Box through MCP, giving it a persistent cloud computer for building and running code. The article describes using that setup to create projects, work in GitHub repositories, chain Slack and Linear tasks into pull requests, and have a second bot review changes, with a human reviewing and merging the result.

### Source excerpt

AI assistants like Grok Bot are already useful day to day. Give one an Upstash Box through MCP and it gets a real remote computer you can drive by voice, including from your phone.

## Building A Multi-File Drag-and-Drop Uploader With Upstash Blob

DevFeed: [Building A Multi-File Drag-and-Drop Uploader With Upstash Blob](<https://devfeed.tech/articles/building-a-multi-file-drag-and-drop-uploader-with-upstash-blob-78691.md>)

Original publisher: [Read original article](<https://upstash.com/blog/react-file-upload-a-multi-file-drag-and-drop-uploader-with-upstash-blob>)

Author: Josh

Published: 2026-10-07T00:00:00Z

Content type: tutorial

Language: en

Sources: [Upstash](<https://devfeed.tech/sources/upstash.md>)

Topics: [React](<https://devfeed.tech/topics/react.md>), [react dnd](<https://devfeed.tech/topics/react-dnd.md>)

Tags: [api](<https://devfeed.tech/tags/api.md>), [aws](<https://devfeed.tech/tags/aws.md>), [aws-lambda](<https://devfeed.tech/tags/aws-lambda.md>), [blob](<https://devfeed.tech/tags/blob.md>), [database](<https://devfeed.tech/tags/database.md>), [drag-and-drop](<https://devfeed.tech/tags/drag-and-drop.md>)

### AI overview

A tutorial for building a multi-file photo uploader in a plain React single-page app with Vite, Hono, and Upstash Blob. It explains keeping storage credentials on the server, issuing signed URLs for direct browser uploads, and adding per-file progress, cancellation, retries, and resumable multipart uploads. It also covers repeated completion callbacks, abandoned uploads, untrusted file content, and storage cost tradeoffs.

### Source excerpt

Articles and tutorials on serverless technologies from Upstash and community

## The Best Daytona Alternatives for AI Agent Sandboxes in 2026

DevFeed: [The Best Daytona Alternatives for AI Agent Sandboxes in 2026](<https://devfeed.tech/articles/the-best-daytona-alternatives-for-ai-agent-sandboxes-in-2026-87115.md>)

Original publisher: [Read original article](<https://upstash.com/blog/best-daytona-alternatives>)

Author: Ali Tarık Şahin

Published: 2026-10-06T00:00:00Z

Content type: comparison

Language: en

Sources: [Upstash](<https://devfeed.tech/sources/upstash.md>)

Topics: [Docker Sandboxes](<https://devfeed.tech/topics/docker-sandboxes.md>), [Service fabric](<https://devfeed.tech/topics/service-fabric.md>), [Cloudflare Workers](<https://devfeed.tech/topics/cloudflare-workers.md>), [Ollama](<https://devfeed.tech/topics/ollama.md>)

Tags: [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-agent](<https://devfeed.tech/tags/ai-agent.md>), [alternatives](<https://devfeed.tech/tags/alternatives.md>), [api](<https://devfeed.tech/tags/api.md>), [box](<https://devfeed.tech/tags/box.md>), [cloud](<https://devfeed.tech/tags/cloud.md>), [coding-agents](<https://devfeed.tech/tags/coding-agents.md>), [container](<https://devfeed.tech/tags/container.md>), [containers](<https://devfeed.tech/tags/containers.md>), [daytona](<https://devfeed.tech/tags/daytona.md>), [modal](<https://devfeed.tech/tags/modal.md>), [python](<https://devfeed.tech/tags/python.md>), [sandbox](<https://devfeed.tech/tags/sandbox.md>), [sandboxes](<https://devfeed.tech/tags/sandboxes.md>), [typescript](<https://devfeed.tech/tags/typescript.md>), [vercel](<https://devfeed.tech/tags/vercel.md>)

### AI overview

This comparison explains why software teams might seek alternatives to Daytona and weighs Upstash Box, E2B, Vercel Sandbox, Modal, Tensorlake, and Northflank by coding-agent support, isolation, pricing, compute, and deployment needs. It also outlines Daytona's strengths and trade-offs and notes migration and self-hosting considerations.

### Source excerpt

The best Daytona alternatives in 2026: Upstash Box if your TypeScript or Python team wants coding agents with less integration work, plus E2B, Vercel Sandbox, Modal, Tensorlake and Northflank, and when Daytona is still the better choice.

## How We Built Emoji Search at Dub with Upstash Vector

DevFeed: [How We Built Emoji Search at Dub with Upstash Vector](<https://devfeed.tech/articles/how-we-built-emoji-search-at-dub-with-upstash-vector-78685.md>)

Original publisher: [Read original article](<https://upstash.com/blog/how-we-built-emoji-search-at-dub-with-upstash-vector>)

Author: Steven Tey

Published: 2026-10-05T00:00:00Z

Content type: article

Language: en

Sources: [Upstash](<https://devfeed.tech/sources/upstash.md>)

Topics: [Qdrant](<https://devfeed.tech/topics/qdrant.md>), [hybrid-search](<https://devfeed.tech/topics/hybrid-search.md>), [Embeddings](<https://devfeed.tech/topics/embeddings.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [database](<https://devfeed.tech/tags/database.md>), [embedding](<https://devfeed.tech/tags/embedding.md>), [search](<https://devfeed.tech/tags/search.md>), [vector](<https://devfeed.tech/tags/vector.md>)

### AI overview

Dub replaced repeated calls to a decision model with an Upstash Vector index to find emojis by meaning. The article describes seeding vectors once, embedding each search query, and returning close matches; it also covers rate limits, caching, and costs.

### Source excerpt

How Dub replaced a per-search model call with a single Upstash Vector index to find emoji by meaning, for nearly zero cost.

## Cloud storage API comparison for side projects: pricing, setup, and features

DevFeed: [Cloud storage API comparison for side projects: pricing, setup, and features](<https://devfeed.tech/articles/what-s-the-best-cloud-storage-api-upstash-blob-vs-vercel-blob-others-2026-comparison-78702.md>)

Original publisher: [Read original article](<https://upstash.com/blog/whats-the-best-cloud-storage-api-for-a-side-project>)

Author: Josh

Published: 2026-10-05T00:00:00Z

Content type: comparison

Language: en

Sources: [Upstash](<https://devfeed.tech/sources/upstash.md>)

Topics: [Amazon S3](<https://devfeed.tech/topics/amazon-s3.md>), [Serverless](<https://devfeed.tech/topics/serverless.md>), [Vercel](<https://devfeed.tech/topics/vercel.md>)

Tags: [api](<https://devfeed.tech/tags/api.md>), [aws](<https://devfeed.tech/tags/aws.md>), [blob](<https://devfeed.tech/tags/blob.md>), [cloud](<https://devfeed.tech/tags/cloud.md>), [cloudflare-workers](<https://devfeed.tech/tags/cloudflare-workers.md>), [cloudfront](<https://devfeed.tech/tags/cloudfront.md>), [environment-variables](<https://devfeed.tech/tags/environment-variables.md>), [pricing](<https://devfeed.tech/tags/pricing.md>), [setup](<https://devfeed.tech/tags/setup.md>), [storage](<https://devfeed.tech/tags/storage.md>), [vercel](<https://devfeed.tech/tags/vercel.md>)

### AI overview

The article compares cloud storage options for side projects, weighing free tiers, egress and request fees, setup effort, and serverless support. It recommends Upstash Blob for many Next.js and serverless projects because it offers a simple token-based setup, while noting that Cloudflare R2, S3, Supabase Storage, and Cloudinary may suit projects with different needs.

### Source excerpt

Upstash Blob vs. Vercel Blob vs. UploadThing comparison in pricing and setup for 2026.

[Next page](<https://devfeed.tech/sources/upstash.md?cursor=WyIyMDI2LTEwLTA1VDAwOjAwOjAwKzAwOjAwIiwgIjM1MzAyMDdkLTU2YmItNDE3Zi1iZWM1LWYxYmJlYjQ1NWFhNyJd>)