OpenAI Codex 发布: 0.156.0-alpha.1
Release 0.156.0-alpha.1
接入 API · 个人 AI 解读连接自己的模型解读资讯，浏览新闻无需配置。
AI Agent 智能体
追踪 AI Agent、MCP、模型连接工具、智能体框架和自动化工作流。
176 条资讯按来源发布或更新时间排序
OpenAI Codex 发布: 0.155.0
## New Features - Added experimental `/voice` conversations with live transcripts and microphone controls on supported builds, enabled through `/experimental`. (#43581, #43651, #44331) - The TUI now shows live reasoning summaries in the status row and completi
Claude Code 发布: v2.1.275
## What's changed - Added the signed-in account to Claude apps gateway sign-in: when the gateway names it, you confirm it before the credential is saved, and `/status` shows it - Added a send-now key (ctrl+enter, or ctrl+x ctrl+s) that interrupts the current t
LangChain 发布: langchain-typesafe==0.0.1a2
Initial release release(typesafe): bump to 0.0.1a2 (#40576) feat(typesafe): experimental `AutoModeMiddleware` (#40545) feat(typesafe): experimental `ModelRouterMiddleware` (#40543) fix(typesafe): trace usage metadata (#40570) feat(typesafe): `TypeSafeClassifie
通义千问 Qwen Code 发布: Release v0.24.0-nightly.20260917.f822124af5
## What's Changed * docs(serve): record merged ACP boundary acceptance by @wenshao in https://github.com/QwenLM/qwen-code/pull/12024 * fix(ci): wait for the published export renderer before packaging the VSIX by @yiliang114 in https://github.com/QwenLM/qwen-co
LangChain 发布: langchain-typesafe==0.0.1a1
Initial release feat(typesafe): `TypeSafeClassifier` (#40542)
A shared agentic platform for Wood Mackenzie, on Amazon Bedrock AgentCore
Wood Mackenzie built APEX, a shared agentic AI platform on Amazon Bedrock AgentCore so every team can ship production agents without rebuilding runtime, identity, observability, and guardrails from scratch. Learn why they chose AgentCore, how APEX Studio opera
Implementing defense-in-depth authorization for MCP tools on Amazon Quick
Learn how to enforce defense-in-depth authorization for Model Context Protocol (MCP) tools on Amazon Quick. This walkthrough wires Microsoft Entra ID group and claims-based JWTs through an Amazon Bedrock AgentCore Gateway interceptor to apply per-user, per-too
n8n 发布: n8n@1.123.81
## [1.123.81](https://github.com/n8n-io/n8n/compare/n8n@1.123.80...n8n@1.123.81) (2026-09-17) ### Bug Fixes * **core:** Allow a domain-restricted credential to work in its own node ([#38786](https://github.com/n8n-io/n8n/issues/38786)) ([7e98622](https://githu
n8n 发布: n8n@2.39.7
## [2.39.7](https://github.com/n8n-io/n8n/compare/n8n@2.39.6...n8n@2.39.7) (2026-09-17) ### Bug Fixes * **core:** Keep breaking change detection running when a rule throws ([#38790](https://github.com/n8n-io/n8n/issues/38790)) ([28945cb](https://github.com/n8n
n8n 发布: n8n@2.40.2
## [2.40.2](https://github.com/n8n-io/n8n/compare/n8n@2.40.1...n8n@2.40.2) (2026-09-17) ### Bug Fixes * **core:** Keep breaking change detection running when a rule throws ([#38789](https://github.com/n8n-io/n8n/issues/38789)) ([5b9a126](https://github.com/n8n
通义千问 Qwen Code 发布: Qwen Code Desktop v0.24.0
## What's Changed * fix(cli): scope the ACP permission queue to the session by @chiga0 in https://github.com/QwenLM/qwen-code/pull/11802 * feat(channels): add shared output modes with DingTalk support by @qqqys in https://github.com/QwenLM/qwen-code/pull/11822
Claude Code 发布: v2.1.274
## What's changed - Added a visible warning when memory usage is critical, with steps to free memory or restart safely - Added `CLAUDE_CODE_MCP_STARTUP_WAIT_MS` to bound how long the first non-interactive turn waits for connecting MCP servers (`0` = don't wait
CrewAI 发布: 1.15.22
## What's Changed ### Features - Support aliases as connection identifiers - Record reasons for deployment creation failures - Collect human feedback and pause events in tracing - Add `llm_overlay` context variable to route agent roles to models - Carry `task_
通义千问 Qwen Code 发布: Release v0.24.0-nightly.20260916.b8def02aad
## What's Changed * docs(serve): record merged ACP boundary acceptance by @wenshao in https://github.com/QwenLM/qwen-code/pull/12024 * fix(ci): wait for the published export renderer before packaging the VSIX by @yiliang114 in https://github.com/QwenLM/qwen-co
TensorRT Edge-LLM Completes the MLPerf Edge Agentic Benchmark 6.4x Faster on Jetson AGX Thor
AI agents are moving from cloud data centers to vehicles, robots, and other edge devices. Unlike a chatbot that answers a single prompt, an agent works through...
Improving HCLS AI reasoning with open-source agent skills
AI agents on foundation models often misapply healthcare and life sciences decision frameworks, citing the right guideline but applying it incorrectly. This post shares 38 open-source agent skills across 11 HCLS domains that close this gap, with installation s
LangChain 发布: langchain==1.4.1
Changes since langchain==1.4.0 release(langchain): 1.4.1 (#40498) fix(langchain): preserve open MCP object arguments (#40414) fix(langchain): correct `InterruptOnConfig` documentation (#40140)
Optimizing agent system prompts with Amazon Bedrock AgentCore
AgentCore optimization turns production traces into proposed configuration changes, then validates them before promotion. This technical companion to the launch post explains how the system prompt optimizer's reflector engine works and shares benchmark results
通义千问 Qwen Code 发布: Release v0.24.0
## Highlights _See the complete change list below._ ## Breaking Changes - fix(core)!: let bash expand project directory variables in command hooks ([#11864](https://github.com/QwenLM/qwen-code/pull/11864)) by @qqqys ## Complete Change List ### Features - feat(
通义千问 Qwen Code 发布: Release v0.23.5-preview.0
## What's Changed * test: record what the Windows inode gates are hiding, and un-skip one by @yiliang114 in https://github.com/QwenLM/qwen-code/pull/11853 * fix(cua): preserve Linux observations and REPL diagnostics by @DragonnZhang in https://github.com/QwenL
n8n 发布: n8n@2.39.6
## [2.39.6](https://github.com/n8n-io/n8n/compare/n8n@2.39.5...n8n@2.39.6) (2026-09-16) ### Bug Fixes * **core:** Check Gateway credits eligibility against the correct sub-node ([#38673](https://github.com/n8n-io/n8n/issues/38673)) ([0cf7e99](https://github.co
n8n 发布: n8n@1.123.80
## [1.123.80](https://github.com/n8n-io/n8n/compare/n8n@1.123.79...n8n@1.123.80) (2026-09-16) ### Bug Fixes * **core:** Apply credential allowed domains in declarative node requests ([#38723](https://github.com/n8n-io/n8n/issues/38723)) ([35ffb88](https://gith
n8n 发布: n8n@2.40.1
## [2.40.1](https://github.com/n8n-io/n8n/compare/n8n@2.40.0...n8n@2.40.1) (2026-09-16)
LiteLLM 发布: v1.103.0-dev.1
## Verify Docker Image Signature All LiteLLM Docker images are signed with [cosign](https://docs.sigstore.dev/cosign/overview/). Every release is signed with the same key introduced in [commit `0112e53`](https://github.com/BerriAI/litellm/commit/0112e53046018d
Claude Code 发布: v2.1.273
## What's changed - Added `x-claude-code-request-class`, `x-claude-code-agent-type`, `x-claude-code-prev-tool-durations`, `x-claude-code-compaction` and `x-claude-code-context-compacted` request headers for LLM gateways; opt in with `CLAUDE_CODE_GATEWAY_HINT_H
Optimizing cost and latency with Amazon Bedrock prompt caching
Prompt caching in Amazon Bedrock can cut input token costs by up to 90% when you repeatedly send the same context to foundation models. This post walks through six practical prompt caching scenarios using the Converse API: message content, system prompt, tool
通义千问 Qwen Code 发布: cua-driver-rs v0.20.9
Qwen CUA Driver prebuilt binaries (vendored under `packages/cua-driver`). - **macOS**: codesigned + notarized universal binary + `QwenCuaDriver.app` - **Linux**: unsigned (x86_64 + arm64, glibc 2.31 floor) - **Windows**: unsigned UIAccess worker + native SDK p
Claude Code 发布: v2.1.272
## What's changed - Bug fixes and reliability improvements
Claude Code 发布: v2.1.271
## What's changed - Added fast mode in Claude Code Remote sessions (cloud and self-hosted runners): the host's fast-mode setting or `/fast` typed in the session applies where your organization allows it - Added mouse support to the `/config` panel in fullscree