# open-responses

Open-source specification and ecosystem for interoperable, multi-provider LLM interfaces based on the OpenAI Responses API.

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

## Testing Conversation Preservation Across LLM APIs: A Rule-Based Oracle for Detecting Silent Information Loss

DevFeed: [Testing Conversation Preservation Across LLM APIs: A Rule-Based Oracle for Detecting Silent Information Loss](<https://devfeed.tech/articles/testing-conversation-preservation-across-llm-apis-a-rule-based-oracle-for-detecting-silent-information-loss-131717.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.15543>)

Author: Xin Liu, Xu Han, Yuxin Wang, Haoran Song, Mingjian Zhao, Lei Wang

Published: 2026-11-13T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Artificial Intelligence](<https://devfeed.tech/sources/arxiv-artificial-intelligence.md>), [arXiv: Software Engineering](<https://devfeed.tech/sources/arxiv-software-engineering.md>)

Topics: [open-responses](<https://devfeed.tech/topics/open-responses.md>), [rule-engine](<https://devfeed.tech/topics/rule-engine.md>), [Test-driven development](<https://devfeed.tech/topics/tdd.md>), [Large Language Model](<https://devfeed.tech/topics/llm.md>)

Tags: [agent](<https://devfeed.tech/tags/agent.md>), [apis](<https://devfeed.tech/tags/apis.md>), [compatibility](<https://devfeed.tech/tags/compatibility.md>), [controls](<https://devfeed.tech/tags/controls.md>), [conversations](<https://devfeed.tech/tags/conversations.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [cs-se](<https://devfeed.tech/tags/cs-se.md>), [error](<https://devfeed.tech/tags/error.md>), [evaluation](<https://devfeed.tech/tags/evaluation.md>), [exceptions](<https://devfeed.tech/tags/exceptions.md>), [experiments](<https://devfeed.tech/tags/experiments.md>), [fault-injection](<https://devfeed.tech/tags/fault-injection.md>), [gateways](<https://devfeed.tech/tags/gateways.md>), [generation](<https://devfeed.tech/tags/generation.md>), [human-review](<https://devfeed.tech/tags/human-review.md>), [information](<https://devfeed.tech/tags/information.md>), [interoperability](<https://devfeed.tech/tags/interoperability.md>), [layers](<https://devfeed.tech/tags/layers.md>), [llm](<https://devfeed.tech/tags/llm.md>), [llm-apis](<https://devfeed.tech/tags/llm-apis.md>), [oracle](<https://devfeed.tech/tags/oracle.md>), [testing](<https://devfeed.tech/tags/testing.md>)

### AI overview

The proposed isloss oracle tests whether LLM API translations preserve conversation information, catching losses that ordinary target schema checks can miss. It maps source and translated requests and replies to a shared representation, ConvIR, and uses explicit rules to separate legitimate format changes from avoidable loss and degradation due to target API limits. It needs neither a reference translation nor extra model calls. In evaluation, it detected 76% of planted faults with a 2% false alarm rate. Of 685 completed synthetic request translations, 18.5% passed static target checks while changing information the target could preserve; 36.4% of 558 translated reply streams caused exceptions or silent corruption in at least one tested official OpenAI SDK. Experiments across six models also found behavior changes when tasks depended on translated-away information.

### Source excerpt

arXiv:2611.15543v1 Announce Type: new Abstract: LLM applications increasingly rely on translators and compatibility layers to move conversations across APIs. Yet a translated request can be accepted by the target API while silently losing information about instruction roles, tool interactions, error states, or generation controls. We introduce isloss, a deterministic oracle for testing conversation-information preservation across LLM API translations. It maps source and translated requests and replies to a shared intermediate representation, ConvIR, and applies explicit rules to distinguish legitimate representation changes from information loss. Unlike schema validation or reference-based differential testing, isloss requires neither a reference translation nor additional model calls. It also distinguishes avoidable loss from degradation caused by target API limitations. We evaluate isloss using specification-based fault injection, human review, and experiments on translators, gateways, and client libraries. On held-out tests, it detects 95/125 planted faults (76.0%) with 2/100 false alarms (2.0%). Across a synthetic request suite spanning six configurations of five translator codebases, 127/685 completed translations (18.5%) pass static target checks while silently changing prompt, role, or tool information in ways the target API could have preserved. In translated replies, 203/558 streams (36.4%) cause exceptions or silent corruption in at least one tested official OpenAI SDK. Targeted experiments across six models show that translation-induced changes can alter model behaviour when tasks depend on the affected information. These results establish conversation preservation as a distinct correctness requirement for reliable LLM interoperability, agent execution, and model evaluation.

## Byoky: Open-source wallet for AI API keys

DevFeed: [Byoky: Open-source wallet for AI API keys](<https://devfeed.tech/articles/byoky-open-source-wallet-for-ai-api-keys-111333.md>)

Original publisher: [Read original article](<https://www.helpnetsecurity.com/2026/11/02/byoky-open-source-ai-api-key-wallet/>)

Author: Anamarija Pogorelec

Published: 2026-11-02T06:00:33Z

Content type: article

Language: en

Sources: [Help Net Security](<https://devfeed.tech/sources/help-net-security.md>)

Topics: [Postman Passport](<https://devfeed.tech/topics/postman-passport.md>), [open-responses](<https://devfeed.tech/topics/open-responses.md>), [Ollama](<https://devfeed.tech/topics/ollama.md>), [OpenClaw](<https://devfeed.tech/topics/openclaw.md>), [Open Source](<https://devfeed.tech/topics/open-source.md>)

Tags: [aes](<https://devfeed.tech/tags/aes.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-api-keys](<https://devfeed.tech/tags/ai-api-keys.md>), [android-apps](<https://devfeed.tech/tags/android-apps.md>), [anthropic](<https://devfeed.tech/tags/anthropic.md>), [api-security](<https://devfeed.tech/tags/api-security.md>), [authentication](<https://devfeed.tech/tags/authentication.md>), [bridge](<https://devfeed.tech/tags/bridge.md>), [chrome](<https://devfeed.tech/tags/chrome.md>), [claude](<https://devfeed.tech/tags/claude.md>), [claude-code](<https://devfeed.tech/tags/claude-code.md>), [cohere](<https://devfeed.tech/tags/cohere.md>), [command-line](<https://devfeed.tech/tags/command-line.md>), [digital-wallet](<https://devfeed.tech/tags/digital-wallet.md>), [don-t-miss](<https://devfeed.tech/tags/don-t-miss.md>), [encrypted](<https://devfeed.tech/tags/encrypted.md>), [firefox](<https://devfeed.tech/tags/firefox.md>), [github](<https://devfeed.tech/tags/github.md>), [google-gemini](<https://devfeed.tech/tags/google-gemini.md>), [gpt](<https://devfeed.tech/tags/gpt.md>), [hermes](<https://devfeed.tech/tags/hermes.md>), [ios](<https://devfeed.tech/tags/ios.md>), [news](<https://devfeed.tech/tags/news.md>), [open-source](<https://devfeed.tech/tags/open-source.md>), [openai](<https://devfeed.tech/tags/openai.md>), [software](<https://devfeed.tech/tags/software.md>), [token](<https://devfeed.tech/tags/token.md>), [wallet](<https://devfeed.tech/tags/wallet.md>)

### AI overview

Byoky keeps AI provider keys encrypted in a user-controlled wallet and sends approved app requests to providers itself, returning session tokens so apps do not receive the underlying keys. Users unlock the wallet with a password of at least 12 characters; the excerpt says keys are encrypted with AES-256-GCM using a key derived through 600,000 PBKDF2 rounds. Users can approve or revoke app access, set per-app spending caps, and review a local request log. Byoky supports browser extensions and iOS and Android apps, 13 cloud providers plus local Ollama and LM Studio, and format translation across Anthropic, OpenAI, Gemini, and Cohere. Developers can use Byoky's SDK with official provider libraries; command-line agents connect through a local proxy requiring a bridge token. The excerpt also says the bridge renames tools and moves the system prompt for third-party agents using Claude Pro or Max tokens, to satisfy Anthropic's first-party detection.

### Source excerpt

Byoky is an open-source wallet for AI API keys, available as a Chrome and Firefox extension and as iOS and Android apps. Users store their keys for OpenAI, Anthropic, Google Gemini and other providers in it, encrypted on their own device. Apps that want those keys ask the wallet for access, and the wallet sends each request to the provider itself. The app gets a session token. The key stays in the wallet. Byoky goes ... More -> The post Byoky: Open-source wallet for AI API keys appeared first on Help Net Security.

## Strix now supports Vercel AI Gateway

DevFeed: [Strix now supports Vercel AI Gateway](<https://devfeed.tech/articles/strix-now-supports-vercel-ai-gateway-106849.md>)

Original publisher: [Read original article](<https://vercel.com/changelog/strix-now-supports-vercel-ai-gateway>)

Author: Harpreet Arora

Published: 2026-10-29T18:44:00Z

Content type: release

Language: en

Sources: [Vercel News](<https://devfeed.tech/sources/vercel-news.md>)

Topics: [open-responses](<https://devfeed.tech/topics/open-responses.md>), [Vercel](<https://devfeed.tech/topics/vercel.md>), [LLM observability](<https://devfeed.tech/topics/llm-observability.md>), [LLM security](<https://devfeed.tech/topics/llm-security.md>)

Tags: [ai-penetration-testing](<https://devfeed.tech/tags/ai-penetration-testing.md>), [anthropic](<https://devfeed.tech/tags/anthropic.md>), [api](<https://devfeed.tech/tags/api.md>), [api-key](<https://devfeed.tech/tags/api-key.md>), [cost](<https://devfeed.tech/tags/cost.md>), [deepseek](<https://devfeed.tech/tags/deepseek.md>), [glm](<https://devfeed.tech/tags/glm.md>), [glm-5-3](<https://devfeed.tech/tags/glm-5-3.md>), [guide](<https://devfeed.tech/tags/guide.md>), [kimi](<https://devfeed.tech/tags/kimi.md>), [llm](<https://devfeed.tech/tags/llm.md>), [open-source](<https://devfeed.tech/tags/open-source.md>), [openai](<https://devfeed.tech/tags/openai.md>), [vercel](<https://devfeed.tech/tags/vercel.md>), [vercel-ai-gateway](<https://devfeed.tech/tags/vercel-ai-gateway.md>)

### AI overview

Strix now supports Vercel AI Gateway, letting it use models from providers including Anthropic, OpenAI, Kimi, GLM, and Deepseek through one API. The source says Gateway usage and cost are tracked across models and that users no longer need separate provider sign-ups. Configure it with `STRIX_LLM` set to `vercel_ai_gateway/<provider>/<model>` and `LLM_API_KEY` set to an AI Gateway key; the example uses `vercel_ai_gateway/zai/glm-5.3`.

### Source excerpt

Strix, the open-source AI penetration testing tool, can now run on any of the 400+ models on Vercel AI Gateway. Strix can reach models from Anthropic, OpenAI, Kimi, GLM, Deepseek, and others through a single API with no markup, removing the need to sign up for multiple providers. Usage and cost are tracked across all models in AI Gateway. Strix selects the Gateway through STRIX_LLM, where the model is the standard AI Gateway <provider>/<model> ID behind a vercel_ai_gateway/ prefix: See Strix's AI Gateway setup guide to configure it and get started today. Read more

## Agentic AI Foundation adds four more open-source AI tools

DevFeed: [Agentic AI Foundation adds four more open-source AI tools](<https://devfeed.tech/articles/agentic-ai-foundation-adds-four-more-open-source-ai-tools-96428.md>)

Original publisher: [Read original article](<https://siliconangle.com/2026/10/22/agentic-ai-foundation-adds-four-more-open-source-ai-tools/>)

Author: Maria Deutscher

Published: 2026-10-22T22:43:47Z

Content type: news

Language: en

Sources: [SiliconANGLE](<https://devfeed.tech/sources/siliconangle.md>)

Topics: [open-responses](<https://devfeed.tech/topics/open-responses.md>), [openenv](<https://devfeed.tech/topics/openenv.md>), [Open Source](<https://devfeed.tech/topics/open-source.md>), [Agentic AI](<https://devfeed.tech/topics/what-is-agentic-ai.md>), [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [linux foundation](<https://devfeed.tech/topics/linux-foundation.md>)

Tags: [agent-skills](<https://devfeed.tech/tags/agent-skills.md>), [agentic](<https://devfeed.tech/tags/agentic.md>), [agentic-ai](<https://devfeed.tech/tags/agentic-ai.md>), [agentic-ai-foundation](<https://devfeed.tech/tags/agentic-ai-foundation.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-agent](<https://devfeed.tech/tags/ai-agent.md>), [ai-tools](<https://devfeed.tech/tags/ai-tools.md>), [alibaba](<https://devfeed.tech/tags/alibaba.md>), [alibaba-group](<https://devfeed.tech/tags/alibaba-group.md>), [anthropic](<https://devfeed.tech/tags/anthropic.md>), [anthropic-pbc](<https://devfeed.tech/tags/anthropic-pbc.md>), [artificial-intelligence](<https://devfeed.tech/tags/artificial-intelligence.md>), [hugging-face](<https://devfeed.tech/tags/hugging-face.md>), [hugging-face-inc](<https://devfeed.tech/tags/hugging-face-inc.md>), [linux-foundation](<https://devfeed.tech/tags/linux-foundation.md>), [llm](<https://devfeed.tech/tags/llm.md>), [news](<https://devfeed.tech/tags/news.md>), [open-responses](<https://devfeed.tech/tags/open-responses.md>), [open-source](<https://devfeed.tech/tags/open-source.md>), [open-source-ai](<https://devfeed.tech/tags/open-source-ai.md>), [open-source-ai-tools](<https://devfeed.tech/tags/open-source-ai-tools.md>), [openai](<https://devfeed.tech/tags/openai.md>), [openai-group](<https://devfeed.tech/tags/openai-group.md>), [openai-group-pbc](<https://devfeed.tech/tags/openai-group-pbc.md>), [sandbox](<https://devfeed.tech/tags/sandbox.md>), [the-latest](<https://devfeed.tech/tags/the-latest.md>), [top-story-4](<https://devfeed.tech/tags/top-story-4.md>), [top-story-6](<https://devfeed.tech/tags/top-story-6.md>)

### AI overview

The Agentic AI Foundation now maintains 10 projects, up from three at launch, after accepting four contributions: Open Responses from OpenAI, Agent Skills from Anthropic, OpenEnv from Hugging Face, and OpenSandbox from Alibaba. Open Responses standardizes AI model API implementations so code can move between compatible APIs with fewer major changes; the article says OpenAI workloads can move to and from APIs based on the format. Agent Skills standardizes packages of instructions, examples, and scripts to ease sharing and give agents consistently structured resources. For sandbox-based model training, OpenEnv reduces work when switching training systems, while OpenSandbox provides APIs to manage sandboxes, including connecting agents inside them to external applications.

### Source excerpt

The Agentic AI Foundation, a consortium that maintains open-source artificial intelligence tools, today took four new projects under its wing. The technologies were donated by OpenAI Group PBC, Anthropic PBC, Hugging Face Inc. and Alibaba Group Holding Ltd. They bring the total number of projects maintained by the AAIF to 10. That's up from the [...] The post Agentic AI Foundation adds four more open-source AI tools appeared first on SiliconANGLE.

## Open Responses Joins AAIF with AWS Support

DevFeed: [Open Responses Joins AAIF with AWS Support](<https://devfeed.tech/articles/open-responses-joins-aaif-with-aws-support-95952.md>)

Original publisher: [Read original article](<https://aws.amazon.com/blogs/opensource/open-responses-joins-aaif-with-aws-support/>)

Author: Anthony Liguori

Published: 2026-10-22T16:12:54Z

Content type: article

Language: en

Sources: [AWS Open Source Blog](<https://devfeed.tech/sources/aws-open-source-blog.md>)

Topics: [open-responses](<https://devfeed.tech/topics/open-responses.md>), [Open Source](<https://devfeed.tech/topics/open-source.md>), [AI Context Management](<https://devfeed.tech/topics/ai-context-management.md>), [Ollama](<https://devfeed.tech/topics/ollama.md>), [vllm](<https://devfeed.tech/topics/vllm.md>), [Amazon Bedrock Guardrails](<https://devfeed.tech/topics/amazon-bedrock-guardrails.md>)

Tags: [agentic-ai-foundation](<https://devfeed.tech/tags/agentic-ai-foundation.md>), [ai](<https://devfeed.tech/tags/ai.md>), [amazon-bedrock](<https://devfeed.tech/tags/amazon-bedrock.md>), [api](<https://devfeed.tech/tags/api.md>), [aws](<https://devfeed.tech/tags/aws.md>), [open-responses](<https://devfeed.tech/tags/open-responses.md>), [open-source](<https://devfeed.tech/tags/open-source.md>), [openai](<https://devfeed.tech/tags/openai.md>), [specification](<https://devfeed.tech/tags/specification.md>)

### AI overview

Open Responses has joined the Agentic AI Foundation (AAIF), placing its open API specification under vendor-neutral governance alongside MCP and A2A. The spec defines shared request and response schemas, tool-use patterns, context items, and semantic streaming events, with namespaced extensions and compliance tests. It aims to let applications use or switch among providers without rewriting orchestration logic. AWS contributes engineering support, and Amazon Bedrock supports the Responses API across models from multiple providers, with stateful conversations, built-in tools, and streaming or non-streaming modes. The article says OpenAI SDK users can call Bedrock models by changing the base URL and API key. The specification is still evolving; recent additions include WebSocket transport and a compaction endpoint.

### Source excerpt

The API format that a growing number of model providers use to call language models now has a vendor-neutral home. Open Responses has joined the Agentic AI Foundation (AAIF) as a project, bringing it under open governance alongside MCP and A2A. Based on the OpenAI Open Responses API, Open Responses is an open source specification [...]

## Muse Spark Open now available on AI Gateway

DevFeed: [Muse Spark Open now available on AI Gateway](<https://devfeed.tech/articles/muse-spark-open-now-available-on-ai-gateway-88227.md>)

Original publisher: [Read original article](<https://vercel.com/changelog/muse-spark-open-now-available-on-ai-gateway>)

Author: Zachary Chen

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

Content type: release

Language: en

Sources: [Vercel News](<https://devfeed.tech/sources/vercel-news.md>)

Topics: [Claude](<https://devfeed.tech/topics/claude.md>), [Advanced AI workflows](<https://devfeed.tech/topics/advanced-ai-workflows.md>), [AI Chat](<https://devfeed.tech/topics/ai-chat.md>), [context window](<https://devfeed.tech/topics/context-window.md>), [vercel ai sdk](<https://devfeed.tech/topics/vercel-ai-sdk.md>), [Chat completions endpoints](<https://devfeed.tech/topics/chat-completions-endpoints.md>), [open-responses](<https://devfeed.tech/topics/open-responses.md>), [codex](<https://devfeed.tech/topics/codex.md>)

Tags: [agentic](<https://devfeed.tech/tags/agentic.md>), [agentic-workflows](<https://devfeed.tech/tags/agentic-workflows.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-gateway](<https://devfeed.tech/tags/ai-gateway.md>), [ai-sdk](<https://devfeed.tech/tags/ai-sdk.md>), [api](<https://devfeed.tech/tags/api.md>), [cli](<https://devfeed.tech/tags/cli.md>), [code](<https://devfeed.tech/tags/code.md>), [coding](<https://devfeed.tech/tags/coding.md>), [coding-agents](<https://devfeed.tech/tags/coding-agents.md>), [context](<https://devfeed.tech/tags/context.md>), [context-window](<https://devfeed.tech/tags/context-window.md>), [data-retention](<https://devfeed.tech/tags/data-retention.md>), [failover](<https://devfeed.tech/tags/failover.md>), [keys](<https://devfeed.tech/tags/keys.md>), [muse-spark](<https://devfeed.tech/tags/muse-spark.md>), [muse-spark-open](<https://devfeed.tech/tags/muse-spark-open.md>), [open](<https://devfeed.tech/tags/open.md>), [playground](<https://devfeed.tech/tags/playground.md>), [spark](<https://devfeed.tech/tags/spark.md>)

### AI overview

Vercel has added Meta's open-weight Muse Spark Open reasoning model to AI Gateway. The model targets coding and agentic workflows such as multi-file refactoring, debugging, and large-codebase analysis, with text and image input and a 1M-token context window. It is available through several API formats and coding agents, and AI Gateway provides usage and cost tracking, retries, failover, and related controls.

### Source excerpt

Muse Spark Open from Meta is now available on AI Gateway. The open-weight reasoning model is designed for coding and agentic workflows, including multi-file refactoring, debugging, and understanding large codebases. Muse Spark Open supports text and image input with a 1M-token context window, allowing agents to work with code and screenshots in the same request. It is available with ZDR and no training, without creating separate provider accounts. Use meta/muse-spark-open as the model name across all API formats and coding agents. The model is available across the AI SDK, the OpenAI-compatible Chat Completions and Responses APIs, the Anthropic-compatible Messages API, and coding agents connected to AI Gateway. To use it in Claude Code, Codex, Cursor, and more, install the latest Vercel CLI and run setup: Then select meta/muse-spark-open in the agent. See the coding agents guide for details. Try Muse Spark Open in the model playground. AI Gateway provides a unified API for calling models, tracking usage and cost, and configuring retries, failover, and performance optimizations for higher-than-provider uptime. It includes built-in custom reporting, Zero Data Retention support, budgets for API keys, routing rules, and more. AI Gateway reflects provider pricing with no markup and does not charge a platform fee on inference, including on Bring Your Own Key (BYOK) requests. You can view all language models available on AI Gateway. Read more

## OpenAI's Decisions API lost Nilforoshan's benchmark

DevFeed: [OpenAI's Decisions API lost Nilforoshan's benchmark](<https://devfeed.tech/articles/openai-s-decisions-api-lost-nilforoshan-s-benchmark-85349.md>)

Original publisher: [Read original article](<https://jevdaily.com/issues/2026-10-12-w7>)

Author: Jev Weekly

Published: 2026-10-12T17:00:00Z

Content type: news

Language: en

Sources: [Jev Daily](<https://devfeed.tech/sources/jev-daily.md>)

Topics: [Calculate Pi](<https://devfeed.tech/topics/calculate-pi.md>), [API](<https://devfeed.tech/topics/api.md>), [open-responses](<https://devfeed.tech/topics/open-responses.md>), [human review](<https://devfeed.tech/topics/human-review.md>), [AI Models](<https://devfeed.tech/topics/ai-models.md>), [Multi-step AI processes](<https://devfeed.tech/topics/multi-step-ai-processes.md>)

Tags: [agent](<https://devfeed.tech/tags/agent.md>), [also-on-the-timeline](<https://devfeed.tech/tags/also-on-the-timeline.md>), [api](<https://devfeed.tech/tags/api.md>), [built-with-it](<https://devfeed.tech/tags/built-with-it.md>), [comparisons](<https://devfeed.tech/tags/comparisons.md>), [cost](<https://devfeed.tech/tags/cost.md>), [decisions-api](<https://devfeed.tech/tags/decisions-api.md>), [developer](<https://devfeed.tech/tags/developer.md>), [eval](<https://devfeed.tech/tags/eval.md>), [mcp](<https://devfeed.tech/tags/mcp.md>), [relevance](<https://devfeed.tech/tags/relevance.md>), [someone-measured-it](<https://devfeed.tech/tags/someone-measured-it.md>), [writing-criteria](<https://devfeed.tech/tags/writing-criteria.md>)

### AI overview

Hamed Nilforoshan compared Jev with OpenAI's Decisions API on a production task scoring how relevant resumes or queries were to job descriptions. He reported that OpenAI was twice as expensive and 5-10% worse. The roundup also describes Jev's email service for agents, other model comparisons, and a recipe for evaluating prompts and models.

### Source excerpt

Hamed Nilforoshan ran OpenAI's Decisions API against Jev on a production relevance task and found OpenAI 2x more expensive and 5 to 10% worse. Every number...

## OpenAI Decisions API Hits Public Beta With 10x Faster Typed Answers

DevFeed: [OpenAI Decisions API Hits Public Beta With 10x Faster Typed Answers](<https://devfeed.tech/articles/openai-decisions-api-hits-public-beta-with-10x-faster-typed-answers-84395.md>)

Original publisher: [Read original article](<https://www.marktechpost.com/2026/10/09/openai-decisions-api-hits-public-beta-with-10x-faster-typed-answers/>)

Author: Sana Hassan

Published: 2026-10-09T20:05:07Z

Content type: news

Language: en

Sources: [MarkTechPost](<https://devfeed.tech/sources/marktechpost.md>)

Topics: [ChatGPT API](<https://devfeed.tech/topics/chatgpt-api.md>), [open-responses](<https://devfeed.tech/topics/open-responses.md>), [AI Chat](<https://devfeed.tech/topics/ai-chat.md>)

Tags: [agentic-ai](<https://devfeed.tech/tags/agentic-ai.md>), [ai-agents](<https://devfeed.tech/tags/ai-agents.md>), [ai-infrastructure](<https://devfeed.tech/tags/ai-infrastructure.md>), [ai-shorts](<https://devfeed.tech/tags/ai-shorts.md>), [applications](<https://devfeed.tech/tags/applications.md>), [artificial-intelligence](<https://devfeed.tech/tags/artificial-intelligence.md>), [decisions-api](<https://devfeed.tech/tags/decisions-api.md>), [editors-pick](<https://devfeed.tech/tags/editors-pick.md>), [for-devs](<https://devfeed.tech/tags/for-devs.md>), [gpt-6](<https://devfeed.tech/tags/gpt-6.md>), [gpt-6-luna](<https://devfeed.tech/tags/gpt-6-luna.md>), [machine-learning](<https://devfeed.tech/tags/machine-learning.md>), [new-releases](<https://devfeed.tech/tags/new-releases.md>), [openai](<https://devfeed.tech/tags/openai.md>), [public-beta](<https://devfeed.tech/tags/public-beta.md>), [software-engineering](<https://devfeed.tech/tags/software-engineering.md>), [staff](<https://devfeed.tech/tags/staff.md>), [tech-news](<https://devfeed.tech/tags/tech-news.md>), [technology](<https://devfeed.tech/tags/technology.md>), [uncategorized](<https://devfeed.tech/tags/uncategorized.md>)

### AI overview

OpenAI has released the Decisions API in public beta on GPT-6 Luna. It returns typed answers--probabilities, choices, or scores--from text and image inputs, for software that needs structured decisions rather than generated prose. OpenAI says it is about 10 times faster than the Responses API; the article notes that independent accuracy and calibration data has not been published. Input costs $0.10 per million tokens, with no output-token charges.

### Source excerpt

OpenAI's Decisions API is now in public beta on GPT-6 Luna. It returns typed probabilities, choices and scores about 10x faster than the Responses API, billing $0.10 per 1M input tokens with no output charges. The post OpenAI Decisions API Hits Public Beta With 10x Faster Typed Answers appeared first on MarkTechPost.

## llm-openai-decisions 0.1a0

DevFeed: [llm-openai-decisions 0.1a0](<https://devfeed.tech/articles/llm-openai-decisions-0-1a0-66394.md>)

Original publisher: [Read original article](<https://simonwillison.net/2026/Oct/6/llm-openai-decisions/>)

Author: Simon Willison

Published: 2026-10-06T23:04:13Z

Content type: release

Language: en

Sources: [Simon Willison's Weblog](<https://devfeed.tech/sources/simon-willison-s-weblog.md>)

Topics: [ChatGPT API](<https://devfeed.tech/topics/chatgpt-api.md>), [open-responses](<https://devfeed.tech/topics/open-responses.md>), [Large Language Model](<https://devfeed.tech/topics/llm.md>)

Tags: [api](<https://devfeed.tech/tags/api.md>), [coding-agents](<https://devfeed.tech/tags/coding-agents.md>), [coding-agents-255](<https://devfeed.tech/tags/coding-agents-255.md>), [jev](<https://devfeed.tech/tags/jev.md>), [jev-3](<https://devfeed.tech/tags/jev-3.md>), [llm](<https://devfeed.tech/tags/llm.md>), [llm-638](<https://devfeed.tech/tags/llm-638.md>), [openai](<https://devfeed.tech/tags/openai.md>), [openai-472](<https://devfeed.tech/tags/openai-472.md>)

### AI overview

A release post introduces the llm-openai-decisions plugin, built to work with OpenAI's Jev-style Decisions API. It describes the gpt-6-luna model's image input, compares input-token pricing with Jev, and shows an example image query.

### Source excerpt

Release: llm-openai-decisions 0.1a0 OpenAI released their new Jev-style Decisions API, as previously announced at last week's DevDay. Since I already have an llm-typesafe plugin for talking to Jev, I had GPT-6 Astra read the new OpenAI API documentation and build an llm-openai-decisions plugin inspired by llm-typesafe. Unlike Jev, the new gpt-6-luna decision model supports image input in addition to text. Both models charge for input it and not for output: OpenAI's is 10 cents per million input tokens, Jev's is 4.2 cents per million. Otherwise the API shape is very similar to Jev, at least conceptually. Jev supports three question types for yes/no, choices, or scores. OpenAI Decisions supports the same three types. Install the plugin like this: llm install llm-openai-decisions Here's an example query against an image attachment: llm -m openai-decisions/gpt-6-luna \ -a https://static.simonwillison.net/static/2025/two-pelicans.jpg \ -s 'Does this image contain any mammals?' And example output: {"type": "predicate", "name": "evaluation", "probability": 0.0} Consult the README for full details of how to run the other types of questions. Tags: openai, llm, coding-agents, jev

## Introducing GLM 5.3 on Amazon Bedrock

DevFeed: [Introducing GLM 5.3 on Amazon Bedrock](<https://devfeed.tech/articles/introducing-glm-5-3-on-amazon-bedrock-65182.md>)

Original publisher: [Read original article](<https://aws.amazon.com/blogs/machine-learning/introducing-glm-5-3-on-amazon-bedrock/>)

Author: Alex Thewsey

Published: 2026-10-05T23:25:17Z

Content type: tutorial

Language: en

Sources: [Artificial Intelligence](<https://devfeed.tech/sources/artificial-intelligence.md>)

Topics: [LLM observability](<https://devfeed.tech/topics/llm-observability.md>), [Loop Engineering](<https://devfeed.tech/topics/loop-engineering.md>), [open-responses](<https://devfeed.tech/topics/open-responses.md>), [AI Chat](<https://devfeed.tech/topics/ai-chat.md>), [Amazon Bedrock Knowledge Bases](<https://devfeed.tech/topics/amazon-bedrock-knowledge-bases.md>), [llm-reasoning](<https://devfeed.tech/topics/llm-reasoning.md>)

Tags: [advanced-300](<https://devfeed.tech/tags/advanced-300.md>), [agentic](<https://devfeed.tech/tags/agentic.md>), [ai](<https://devfeed.tech/tags/ai.md>), [amazon-bedrock](<https://devfeed.tech/tags/amazon-bedrock.md>), [announcements](<https://devfeed.tech/tags/announcements.md>), [apis](<https://devfeed.tech/tags/apis.md>), [caching](<https://devfeed.tech/tags/caching.md>), [cost](<https://devfeed.tech/tags/cost.md>), [glm-5-3](<https://devfeed.tech/tags/glm-5-3.md>), [latency](<https://devfeed.tech/tags/latency.md>), [open-source](<https://devfeed.tech/tags/open-source.md>), [security](<https://devfeed.tech/tags/security.md>)

### AI overview

GLM 5.3, a 753B-parameter mixture-of-experts model from Z.ai, is available on Amazon Bedrock for coding and long-running agentic tasks. The tutorial explains how to call it through OpenAI-compatible APIs, use prompt caching to reduce latency and input costs, and run an authorized security test with the open-source Strix agent.

### Source excerpt

GLM 5.3 from Z.ai is now available on Amazon Bedrock: a 753B-parameter mixture-of-experts model built for coding and long-horizon agentic tasks. Learn how to invoke it with the OpenAI-compatible APIs, cut cost and latency with prompt caching, and run an authorized security test with the open-source Strix agent.

## How to Implement Tool Calling in an AI Agent With Python

DevFeed: [How to Implement Tool Calling in an AI Agent With Python](<https://devfeed.tech/articles/how-to-implement-tool-calling-in-an-ai-agent-with-python-50851.md>)

Original publisher: [Read original article](<https://www.sitepoint.com/how-to-implement-tool-calling-in-an-ai-agent-with-python/>)

Author: Tech Team

Published: 2026-09-11T15:16:31Z

Content type: tutorial

Language: en

Sources: [SitePoint](<https://devfeed.tech/sources/sitepoint.md>)

Topics: [AI Agent](<https://devfeed.tech/topics/ai-agent.md>), [Python](<https://devfeed.tech/topics/python.md>), [open-responses](<https://devfeed.tech/topics/open-responses.md>), [OpenAI](<https://devfeed.tech/topics/openai.md>), [Pydantic](<https://devfeed.tech/topics/pydantic.md>), [API](<https://devfeed.tech/topics/api.md>), [SDK](<https://devfeed.tech/topics/sdk.md>)

Tags: [agent](<https://devfeed.tech/tags/agent.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-agent](<https://devfeed.tech/tags/ai-agent.md>), [api](<https://devfeed.tech/tags/api.md>), [automation](<https://devfeed.tech/tags/automation.md>), [how-to](<https://devfeed.tech/tags/how-to.md>), [implement](<https://devfeed.tech/tags/implement.md>), [openai-api](<https://devfeed.tech/tags/openai-api.md>), [python](<https://devfeed.tech/tags/python.md>), [sdk](<https://devfeed.tech/tags/sdk.md>), [setup](<https://devfeed.tech/tags/setup.md>)

### AI overview

A step-by-step tutorial on implementing tool calling in an AI agent with Python. It uses the OpenAI Responses API and Pydantic to define tools, execute matching Python functions, and return results to the model in a flight-status example.

### Source excerpt

null Continue reading How to Implement Tool Calling in an AI Agent With Python on SitePoint.

## Use any\* LLM with @mux/ai

DevFeed: [Use any\* LLM with @mux/ai](<https://devfeed.tech/articles/use-any-llm-with-mux-ai-77960.md>)

Original publisher: [Read original article](<https://www.mux.com/blog/use-any-llm-with-mux-ai>)

Author: Phil Cluff; Joshua Alphonse; Victor Boutté

Published: 2026-09-03T17:05:01Z

Content type: release

Language: en

Sources: [Mux Blog - Video technology and more](<https://devfeed.tech/sources/mux-blog-video-technology-and-more.md>)

Topics: [Large Language Model](<https://devfeed.tech/topics/llm.md>), [open-responses](<https://devfeed.tech/topics/open-responses.md>), [Ollama](<https://devfeed.tech/topics/ollama.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [ai-sdk](<https://devfeed.tech/tags/ai-sdk.md>), [baseten](<https://devfeed.tech/tags/baseten.md>), [llm](<https://devfeed.tech/tags/llm.md>), [open-weight-models](<https://devfeed.tech/tags/open-weight-models.md>), [openai-api](<https://devfeed.tech/tags/openai-api.md>), [product](<https://devfeed.tech/tags/product.md>)

### AI overview

Mux has added Baseten and general OpenAI-compatible providers to @mux/ai, enabling workflows to use open-weight models through hosted services or self-hosted endpoints. Video workflows require vision and structured-output support; some endpoint limitations can be addressed with base64 image submission. The article also describes model verification, evaluation limits, and retry handling for occasional truncated responses.

### Source excerpt

We've made it easy to use @mux/ai with Baseten or any other OpenAI API compatible LLM, including the latest open-weight models.

## Meet Connery: An Open-Source Plugin Infrastructure for OpenGPTs and LLM apps

DevFeed: [Meet Connery: An Open-Source Plugin Infrastructure for OpenGPTs and LLM apps](<https://devfeed.tech/articles/meet-connery-an-open-source-plugin-infrastructure-for-opengpts-and-llm-apps-78339.md>)

Original publisher: [Read original article](<https://www.langchain.com/blog/meet-connery-an-open-source-plugin-infrastructure-for-opengpts-and-llm-apps>)

Author: LangChain Accounts

Published: 2026-08-26T15:02:51Z

Content type: article

Language: en

Sources: [LangChain Blog](<https://devfeed.tech/sources/langchain-blog.md>)

Topics: [open-responses](<https://devfeed.tech/topics/open-responses.md>), [LangChain](<https://devfeed.tech/topics/langchain.md>)

Tags: [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [human-in-the-loop](<https://devfeed.tech/tags/human-in-the-loop.md>), [integrations](<https://devfeed.tech/tags/integrations.md>), [open-source](<https://devfeed.tech/tags/open-source.md>)

### AI overview

Connery is presented as an open-source plugin infrastructure for connecting LLM applications and GPTs to third-party services. The article describes its Runner, plugin and action model, client integrations, and features for authentication, personalization, human review, and auditability. It also walks through a demo in which OpenGPT uses Connery actions to summarize a webpage and send the result by email.

### Source excerpt

Discover Connery: open-source plugin infrastructure for LLM apps. Secure integrations, personalization, and human-in-the-loop control for AI agents.

## OpenRouter vs Portkey: Which LLM Gateway for Your Team?

DevFeed: [OpenRouter vs Portkey: Which LLM Gateway for Your Team?](<https://devfeed.tech/articles/openrouter-vs-portkey-which-llm-gateway-for-your-team-78622.md>)

Original publisher: [Read original article](<https://openrouter.ai/blog/insights/openrouter-vs-portkey/>)

Author: OpenRouter

Published: 2026-06-19T19:00:00Z

Content type: comparison

Language: en

Sources: [OpenRouter](<https://devfeed.tech/sources/openrouter.md>)

Topics: [gateway](<https://devfeed.tech/topics/gateway.md>), [open-responses](<https://devfeed.tech/topics/open-responses.md>), [LLM security](<https://devfeed.tech/topics/llm-security.md>)

Tags: [ai-gateway](<https://devfeed.tech/tags/ai-gateway.md>), [compliance](<https://devfeed.tech/tags/compliance.md>), [llm-gateway](<https://devfeed.tech/tags/llm-gateway.md>), [observability](<https://devfeed.tech/tags/observability.md>), [openrouter](<https://devfeed.tech/tags/openrouter.md>)

### AI overview

OpenRouter provides managed routing across model providers, while Portkey adds governance and observability in front of provider accounts a team already operates. The comparison covers model access, failover, compliance, pricing, and ways to use the services together.

### Source excerpt

OpenRouter routes across providers on credits you buy; Portkey governs the provider keys you already have. Here's how they compare on models, observability, compliance, and price.

## Gemini 2.5 Flash API - Pricing, Quickstart & Provider Comparison

DevFeed: [Gemini 2.5 Flash API - Pricing, Quickstart & Provider Comparison](<https://devfeed.tech/articles/gemini-2-5-flash-api-pricing-quickstart-provider-comparison-78644.md>)

Original publisher: [Read original article](<https://openrouter.ai/blog/tutorials/gemini-25-flash-api-pricing-quickstart-provider-comparison/>)

Author: OpenRouter

Published: 2026-06-09T16:00:00Z

Content type: tutorial

Language: en

Sources: [OpenRouter](<https://devfeed.tech/sources/openrouter.md>)

Topics: [Claude](<https://devfeed.tech/topics/claude.md>), [open-responses](<https://devfeed.tech/topics/open-responses.md>), [Chat completions endpoints](<https://devfeed.tech/topics/chat-completions-endpoints.md>), [ChatGPT API](<https://devfeed.tech/topics/chatgpt-api.md>)

Tags: [2026](<https://devfeed.tech/tags/2026.md>), [comparison](<https://devfeed.tech/tags/comparison.md>), [gemini](<https://devfeed.tech/tags/gemini.md>), [pricing](<https://devfeed.tech/tags/pricing.md>), [reasoning](<https://devfeed.tech/tags/reasoning.md>)

### AI overview

This guide explains Gemini 2.5 Flash API pricing, configuring its thinking budget, and making requests through OpenRouter or Google's direct API. It compares providers and related Gemini models, with practical notes on latency, routing, billing, and production constraints. The article also notes that Vertex AI is scheduled to discontinue Gemini 2.5 Flash on October 16, 2026.

### Source excerpt

Overpaying for reasoning you don't need? Learn how to configure Gemini 2.5 Flash API thinking budgets, compare providers, and make your first call in 5 minutes.

## GitHub Copilot bring your own key (BYOK) enhancements

DevFeed: [GitHub Copilot bring your own key (BYOK) enhancements](<https://devfeed.tech/articles/github-copilot-bring-your-own-key-byok-enhancements-72087.md>)

Original publisher: [Read original article](<https://github.blog/changelog/2026-01-15-github-copilot-bring-your-own-key-byok-enhancements>)

Author: Allison

Published: 2026-01-15T20:01:40Z

Content type: release

Language: en

Sources: [GitHub Changelog](<https://devfeed.tech/sources/github-changelog.md>)

Topics: [GitHub Copilot](<https://devfeed.tech/topics/github-copilot.md>), [AI Chat](<https://devfeed.tech/topics/ai-chat.md>), [open-responses](<https://devfeed.tech/topics/open-responses.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [ai-studio](<https://devfeed.tech/tags/ai-studio.md>), [anthropic](<https://devfeed.tech/tags/anthropic.md>), [api](<https://devfeed.tech/tags/api.md>), [api-key](<https://devfeed.tech/tags/api-key.md>), [api-keys](<https://devfeed.tech/tags/api-keys.md>), [apis](<https://devfeed.tech/tags/apis.md>), [aws](<https://devfeed.tech/tags/aws.md>), [aws-bedrock](<https://devfeed.tech/tags/aws-bedrock.md>), [bedrock](<https://devfeed.tech/tags/bedrock.md>), [bring-your-own-key](<https://devfeed.tech/tags/bring-your-own-key.md>), [byok](<https://devfeed.tech/tags/byok.md>), [configuration](<https://devfeed.tech/tags/configuration.md>), [copilot](<https://devfeed.tech/tags/copilot.md>), [enterprises](<https://devfeed.tech/tags/enterprises.md>), [github](<https://devfeed.tech/tags/github.md>), [github-copilot](<https://devfeed.tech/tags/github-copilot.md>), [integrations](<https://devfeed.tech/tags/integrations.md>), [models](<https://devfeed.tech/tags/models.md>), [responses](<https://devfeed.tech/tags/responses.md>)

### AI overview

GitHub Copilot BYOK now supports API keys from AWS Bedrock, Google AI Studio, and OpenAI-compatible providers, alongside Anthropic, Microsoft Foundry, OpenAI, and xAI. It adds support for models using the Responses API, enabling structured outputs and richer multimodal interactions; administrators can set a maximum context window to balance cost, performance, and response quality; and streaming displays output as it is generated. The capabilities are in public preview for GitHub Enterprise and Business customers, who can connect provider keys in enterprise or organization settings for use in Copilot Chat and supported IDEs.

### Source excerpt

Bring your own key (BYOK) for GitHub Copilot now supports additional APIs, new configuration options, and more provider integrations. With this update, enterprises can connect models that use the Responses...

## Open Responses: What you need to know

DevFeed: [Open Responses: What you need to know](<https://devfeed.tech/articles/open-responses-what-you-need-to-know-7426.md>)

Original publisher: [Read original article](<https://huggingface.co/blog/open-responses>)

Author: shaun smith; ben burtenshaw; merve; Pedro Cuenca

Published: 2026-01-15T00:00:00Z

Content type: article

Language: en

Sources: [Hugging Face](<https://devfeed.tech/sources/hugging-face-blog.md>)

Topics: [open-responses](<https://devfeed.tech/topics/open-responses.md>), [API](<https://devfeed.tech/topics/api.md>), [Open Source](<https://devfeed.tech/topics/open-source.md>), [inference-providers](<https://devfeed.tech/topics/inference-providers.md>), [Streaming](<https://devfeed.tech/topics/streaming.md>), [JSON](<https://devfeed.tech/topics/json.md>), [OpenAI](<https://devfeed.tech/topics/openai.md>)

Tags: [agentic](<https://devfeed.tech/tags/agentic.md>), [agents](<https://devfeed.tech/tags/agents.md>), [api](<https://devfeed.tech/tags/api.md>), [apis](<https://devfeed.tech/tags/apis.md>), [autonomous](<https://devfeed.tech/tags/autonomous.md>), [community](<https://devfeed.tech/tags/community.md>), [inference](<https://devfeed.tech/tags/inference.md>), [inference-providers](<https://devfeed.tech/tags/inference-providers.md>), [json](<https://devfeed.tech/tags/json.md>), [mcp](<https://devfeed.tech/tags/mcp.md>), [open-responses](<https://devfeed.tech/tags/open-responses.md>), [open-source](<https://devfeed.tech/tags/open-source.md>), [openai](<https://devfeed.tech/tags/openai.md>), [responses](<https://devfeed.tech/tags/responses.md>), [streaming](<https://devfeed.tech/tags/streaming.md>), [tool](<https://devfeed.tech/tags/tool.md>), [workflow](<https://devfeed.tech/tags/workflow.md>)

### AI overview

Open Responses is presented as an open inference standard for agentic workloads. The article explains how it extends and open-sources the Responses API, supports interoperable routing across inference providers, and introduces standardized configuration, semantic streaming events, extensibility, and optional reasoning fields.

### Source excerpt

We're on a journey to advance and democratize artificial intelligence through open source and open science.

## Building with the OpenAI Apps SDK: A Field Guide

DevFeed: [Building with the OpenAI Apps SDK: A Field Guide](<https://devfeed.tech/articles/building-with-the-openai-apps-sdk-a-field-guide-81860.md>)

Original publisher: [Read original article](<https://render.com/blog/building-with-the-openai-apps-sdk-a-field-guide>)

Published: 2025-10-29T20:33:00Z

Content type: tutorial

Language: en

Sources: [Render](<https://devfeed.tech/sources/render.md>)

Topics: [SDK](<https://devfeed.tech/topics/sdk.md>), [open-responses](<https://devfeed.tech/topics/open-responses.md>), [OpenAI](<https://devfeed.tech/topics/openai.md>), [vercel ai sdk](<https://devfeed.tech/topics/vercel-ai-sdk.md>)

Tags: [debugging](<https://devfeed.tech/tags/debugging.md>), [infrastructure](<https://devfeed.tech/tags/infrastructure.md>), [mcp](<https://devfeed.tech/tags/mcp.md>), [openai](<https://devfeed.tech/tags/openai.md>), [practical](<https://devfeed.tech/tags/practical.md>), [sdk](<https://devfeed.tech/tags/sdk.md>)

### AI overview

A hands-on guide to building an app with OpenAI's Apps SDK, covering MCP architecture, local widget development, debugging response-shape errors, telemetry, and deployment. The author reports that a local harness speeds widget iteration and recommends logging payloads to diagnose generic 424 errors.

### Source excerpt

A practical guide to building with OpenAI's Apps SDK. Learn what to expect from MCP tools, widget development, debugging 424 errors, and infrastructure choices.

## From MCP to multi-agents: The top 10 new open source AI projects on GitHub right now and why they matter

DevFeed: [From MCP to multi-agents: The top 10 new open source AI projects on GitHub right now and why they matter](<https://devfeed.tech/articles/from-mcp-to-multi-agents-the-top-10-new-open-source-ai-projects-on-github-right-now-and-why-they-matter-67548.md>)

Original publisher: [Read original article](<https://github.blog/open-source/maintainers/from-mcp-to-multi-agents-the-top-10-open-source-ai-projects-on-github-right-now-and-why-they-matter/>)

Author: Jeimy Ruiz

Published: 2025-04-30T16:00:49Z

Content type: article

Language: en

Sources: [GitHub Blog](<https://devfeed.tech/sources/github-engineering.md>)

Topics: [Microsoft Agent Framework](<https://devfeed.tech/topics/microsoft-agent-framework.md>), [Open Source](<https://devfeed.tech/topics/open-source.md>), [open-responses](<https://devfeed.tech/topics/open-responses.md>), [Maintainers](<https://devfeed.tech/topics/maintainers.md>), [vercel ai sdk](<https://devfeed.tech/topics/vercel-ai-sdk.md>)

Tags: [agents](<https://devfeed.tech/tags/agents.md>), [ai-agents](<https://devfeed.tech/tags/ai-agents.md>), [generative-ai](<https://devfeed.tech/tags/generative-ai.md>), [insights](<https://devfeed.tech/tags/insights.md>), [maintainers](<https://devfeed.tech/tags/maintainers.md>), [mcp](<https://devfeed.tech/tags/mcp.md>), [news-insights](<https://devfeed.tech/tags/news-insights.md>), [octoverse](<https://devfeed.tech/tags/octoverse.md>), [open-source](<https://devfeed.tech/tags/open-source.md>), [open-source-ai](<https://devfeed.tech/tags/open-source-ai.md>), [research](<https://devfeed.tech/tags/research.md>)

### AI overview

GitHub experts ranked ten recently created open-source AI projects using signals such as stars per day, forks, traffic spikes, and contributor velocity. The article surveys projects involving MCP integrations, multi-agent systems, AI backends, speech tools, and agent portability, and discusses open-source licensing and emerging integration standards.

### Source excerpt

Get insights on the latest trends from GitHub experts while catching up on these exciting new projects.

## How LLMs Could Reduce Duplicate API Connector Work

DevFeed: [How LLMs Could Reduce Duplicate API Connector Work](<https://devfeed.tech/articles/api-connector-revolution-80383.md>)

Original publisher: [Read original article](<https://dlthub.com/blog/recomposable-connectors>)

Author: Adrian Brudaru

Published: 2025-04-15T00:00:00Z

Content type: article

Language: en

Sources: [DLT Hub](<https://devfeed.tech/sources/dlt-hub.md>)

Topics: [API](<https://devfeed.tech/topics/api.md>), [AI connector platforms](<https://devfeed.tech/topics/ai-connector-platforms.md>), [open-responses](<https://devfeed.tech/topics/open-responses.md>)

Tags: [api](<https://devfeed.tech/tags/api.md>), [connectors](<https://devfeed.tech/tags/connectors.md>), [engineering](<https://devfeed.tech/tags/engineering.md>), [interoperability](<https://devfeed.tech/tags/interoperability.md>), [llms](<https://devfeed.tech/tags/llms.md>)

### AI overview

The article argues that LLMs can help convert API connectors across languages and frameworks, reducing repeated work on authentication, rate limits, and pagination. It notes that generation works best with detailed source code and may require further information gathering when based on documentation. It also discusses possible copyright implications of independently rewriting connectors.

### Source excerpt

An introduction to using LLMs to eliminate redundant API connector development, promoting interoperability and shared community insights.