关注连接模型的工具：AI Agent、MCP、模型网关、编程助手、推理引擎和自动化工作流。
## 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
Changes since langchain-core==1.6.1 release(core): 1.6.2 (#40209) feat(openai): support async tools (#40208) chore(deps): bump mistune from 3.3.0 to 3.3.3 in /libs/core (#40150) chore(deps): bump tornado from 6.5.7 to 6.5.8 in /libs/core (#40113) fix(core): av
Enterprise work spans messages, decisions, projects, and obligations that change over time. An AI agent that starts without this context must reconstruct it...
## What's Changed ### Bug Fixes - Fix legacy platform tool alias discovery ### Documentation - Update snapshot and changelog for v1.15.19 ## Contributors @joaomdmoura, @vinibrsl
## What's Changed ### Features - Add Clipper integrations client - Add `now()` to the CEL expression environment - Record how a crew run ended for every user - Report machine size as a coarse band, not a core count - Add injectable client for CrewAI platform t
## What's Changed * gemma4 now supports images and audio on MLX engine * Report cached prompt tokens * Honor GGUF model defined default parameters * MLX, MLX-C, llama.cpp update ## New Contributors * @marcelpetrick made their first contribution in https://gith
Changes since langchain==1.3.18 docs(langchain): runnable `langchain.mcp` examples (#39976) feat(langchain): `langchain.mcp` namespace, `MCPAdapter` (#39939) perf(anthropic,langchain): omit middleware trace inputs (#40098) fix(langchain): include model destina
AI cost optimization goes beyond model selection. Discover how context engineering in Microsoft Foundry helps lower AI costs by improving knowledge retrieval, tool selection, memory, and agent performance at scale. The post The Economics of Agent Optimization:
## What's Changed * fix(kosong): omit empty anthropic-beta header when no beta features declared by @7Sageer in https://github.com/MoonshotAI/kimi-cli/pull/2580 * chore(release): bump kosong to 0.56.0 by @jackfish212 in https://github.com/MoonshotAI/kimi-cli/p
# Introducing Dify Agent *(Beta)*: A New Agent Experience in Dify > [!WARNING] > You should provide Dify Agent services ⚠️**only to trusted, non-malicious users**⚠️. As many of you know, the shell-based LLM agent paradigm has brought a major leap in agent capa
# Dify 1.15.0 Release Note ## What's Changed ### UX & UI Enhancements - **Redesigned landing / onboarding** for an easier first-run experience (#37433, #37844, #37800) - **Faster navigation** — improved "go to anything" palette and autofocused search inputs (#
## New Features **Agent: E2B Sandbox, Home Snapshots, and Skill Management** - **E2B sandbox backend**: agent shell/code execution can now run on [E2B](https://e2b.dev) cloud sandboxes in addition to the local sandbox. Select the backend with `DIFY_AGENT_RUNTI
## What's Changed * Ollama's app now follows the system appearance again, restoring dark mode support * Fixed the macOS app to properly hand off to an already-running instance instead of starting a second one * The Claude Desktop proxy no longer interrupts in-
## What's Changed * fix(formatter): derive audio format from media type by @ump45nose in https://github.com/agentscope-ai/agentscope/pull/2301 * fix(gemini): exclude tool-execution tokens from output_tokens by @iluv7 in https://github.com/agentscope-ai/agentsc
## What's Changed ### Features - Promote conversational flows to stable - Record a created deployment with the given UUID - Enhance conversational flow documentation and APIs - Let a declaration name the router's response format - Let a chat flow declare its o
Atomistic simulation requires three things: knowledge of the science, compute-efficient implementation of simulations, and accessible interfaces to the...
## What's Changed * MLX: Qwen3.8 Flash Next support * cmake: make external compat patches idempotent * MLX and llama.cpp update * mlxrunner: add structured output support * mlxrunner: avoid Metal GPU timeouts when loading models from slow storage ## New Contri
Microsoft Foundry gives you four levers that act on every request, before a single line of agent logic changes. The post The Economics of Agent Optimization: Four ways to lower the cost appeared first on Microsoft Azure Blog.
# Release v5.16.0 ## New Model additions ### Qwen4-Exp Qwen4-Exp builds on Qwen3.5's hybrid text and multimodal architecture with three key components: GatedResidual (GR), Qwen Sparse Attention (QSA), and Per-Layer Embedding (PLE). GR is a Qwen-developed resid
# Release v5.16.1 This is a special release as we include GLM! (and a few small fixes) # GLM-5.3-Flash GLM-5.3-Flash, the first **natively multimodal model** in the GLM-5 series. With 320B total parameters and just 18B active parameters, it outperforms GLM-5.2
One off backport of the FastMCP import warning for `2.0.x`, this is due to a lot of people running into this error and making issues on other repos about it. Ideally either pin `mcp<2` or upgrade to 2. ## What's Changed * [v2.0.x] Point imports of mcp.server.f
## What's Changed ### Claude Desktop Developers can now easily configure Claude Desktop to seamlessly work with Ollama as a third-party gateway provider. ### Improved caching * Fixed a hang where agent clients that cancel long prefills * Prefill restore points
## What's Changed * Point imports of mcp.server.fastmcp at the migration guide by @maxisbey in https://github.com/modelcontextprotocol/python-sdk/pull/3388 **Full Changelog**: https://github.com/modelcontextprotocol/python-sdk/compare/v2.1.0...v2.1.1
## Highlights - `Client` accepts `StdioServerParameters` directly: `Client(StdioServerParameters(command="uv", args=["run", "server.py"]))` (#3321). - Prompt messages accept `Image` and `Audio`, prompt functions may return bare content blocks, and `Message` /
## What's Changed * [v1.x] Complete the FastMCP Settings model at import time by @maxisbey in https://github.com/modelcontextprotocol/python-sdk/pull/3352 * [v1.x] Apply the request body limit to the SSE and OAuth endpoints by @maxisbey in https://github.com/m
## What's Changed * fix(gemini): remove unsupported $schema from tool parameters by @qbc2016 in https://github.com/agentscope-ai/agentscope/pull/2277 * feat(workspace): share workspace across different agents by @iluv7 in https://github.com/agentscope-ai/agent
As AI agents become more capable and operate over longer horizons, building security and trust into the applications they power becomes increasingly important....
A frontier language model is only one component of an AI agent. The surrounding agent system—often called a harness—determines how the model receives...
Long-running AI agents spend most of their time on high-volume execution: tool calls, result validation, and subagent delegation. Using a frontier reasoning...
## What's Changed * New desktop onboarding flow on first launch * Caches resolved model metadata between requests, cutting time-to-first-token by roughly half (TTFT dropped from ~995 ms to ~524 ms in benchmarks) * Fixes a bug where chat and generate could wedg
