Anthropic agents

基于 Claude API 的视觉识别 MCP server:为不支持视觉的主模型多一双眼睛。内部 http 直调视觉网关,图片放 user message 顶层 image content block,tool_result 仅返回文字描述,绕开 tool_result 内嵌 image 的网关兼容缺陷。

Cap-aware tmux scheduler & auto-resume for Claude Code — schedule prompts and keep sessions running through the 5-hour usage limit.

Verifiable multi-agent consensus for Claude. The coordination layer frameworks punted on.

Run large LLMs across two NVIDIA DGX Sparks with vLLM — model picker, one-command start/stop, and an Anthropic-compatible endpoint for Claude Code.

LLM evaluation framework for developers

Genkit Anthropic Plugin (Community)

A glass-box, minimal library for building LLM agents — modern techniques as opt-in primitives, no hidden control flow.

Google-OAuth-gated LLM gateway: verify a Google ID token, then run a Gemini (Vertex AI) completion for the verified caller.

Proxy Gemini (Vertex AI) completions wrapped in OpenTelemetry trace spans; returns the answer plus the trace/span id.

Collaborate with Claude on Jupyter notebook code and documentation

Anthropic Claude agent handler for LaunchDarkly AI SDK

Anthropic Claude messages handler for LaunchDarkly AI SDK

Batch-API-native coding agent: plan realtime, execute on 24h-SLA batch APIs, optimize like a query engine.

Free-first LLM routing for Python: local Ollama -> OpenRouter free models -> paid Anthropic API, with automatic fallback and a savings ledger.

Client-side rate limiting for the Claude API. Never sees your API key.

Shared AWS Bedrock internals (SigV4 signing, event-stream decoding, Anthropic pricing) for lmux

AIGP governance adapter for anthropic

Durable Anthropic Messages adapter for the MemoFlow Python SDK

NextPy AI Agent - Intelligent coding assistant for NextPy framework

OpenTelemetry Anthropic instrumentation

The official Claude Code agent — same as Anthropic's, full coding toolset. GPU via providers.

TAPM v2 hook for Anthropic (in-process library instrumentation)

TechTide Swarm 357 — layered orchestration, durable memory bridge, and observability hooks.

Anthropic integration for telemetry.dev Python SDK

Library to systematically track and evaluate LLM based applications.

Provider-independent AI agent workflow system for Claude Code, Codex, Gemini CLI, and Kimi Code

Google-OAuth-gated LLM gateway: verify a Google ID token, then run a Gemini (Vertex AI) completion for the verified caller.

Outlook Assistant — MCP server with 22 tools for email, calendar, contacts, and settings via Microsoft Graph API

Multi-agent BMAD framework for Claude Code — SPEC → DESIGN → BUILD → QA in one kit.

Self-hosted AI voice agent for Asterisk. Streaming speech-to-text to LLM to text-to-speech over AudioSocket, with barge-in and correct 20 ms frame pacing.

Onion-architected, autonomous Claude Code session runner and full Anthropic SDK CLI — never blocks on a human, distinguishes rate limits from exhausted credits, and resumes safely across usage windows.