#mcp

Local context-compression layer for agent tool outputs. Claude Code PostToolUse hook or generic filter, single Go binary.

Give your agent capabilities, not giant tool walls.

Extended Memory Layer of Coding AI

该仓库未发布描述。

Turns a plain notes repo into a bridge: one repo that holds the plan and drives agentic work across your other repos.

Code search that lets AI coding agents find the right files in fewer steps. Use the hosted endpoint or self-host, works with Claude Code, Copilot and Cursor via MCP.

Audit your AI agent configs before you run them — prompt injection, rogue MCP servers, credential-exfil. Plus dependency vetting.

saige - Super Artificial Intelligence Graph Environment. A unified Go SDK, CLI, and MCP server for streaming AI agents, knowledge graphs, and RAG pipelines, with Ollama, OpenAI, Anthropic, and Google providers behind one interface.

Runtime control, security, and governance for AI agents — decide what an agent may do at the moment it acts, revoke that authority instantly, and keep tamper-evident evidence of every decision.

Slack MCP server for Claude Code, GitHub Copilot, Cursor, JetBrains, and any MCP-compatible client. Morning recaps, decision detection, multi-channel digests.

Open-source WebSocket HTTP/WS reverse tunnel (ngrok alternative) on Cloudflare Workers + Durable Objects — free stable reservable subdomains.

PostgreSQL-native deployment tool where deploy.sql controls transactions, execution order, tests, and error handling.

A firewall and password manager for your AI coding agents.

🌿 Production-grade Go framework for conversational AI agents — LLM abstraction, RAG, memory, WhatsApp, scheduling & observability built in.

MCP server for Kling AI video generation via AceDataCloud API

MCP server for Luma AI video generation via Ace Data Cloud.

MCP server for Google SERP search, images, news, maps, and knowledge graph results.

Claude Code QA agent with memory, plus a read-only MCP server (verdict-qa-mcp on PyPI): baseline → delta runs (NEW/REGRESSED), a fact harness so the model judges while the system measures, signed run history, flaky quarantine with expiry, and an exit-code release gate for CI. Ships six scored eval fixtures — misses published.

Multi-account tool broker for AI agents — use tools on demand from the CLI or connect through MCP, with credentials kept local.

An open source deterministic or LLM-enhanced agent showcasing and implementing the KCP protocol

The self-correcting memory layer for AI agents. Zero-dependency Python memory and MCP server. Supersede, revert, or forget a value deterministically. Verifiable erasure, witness-backed tamper-evident receipts, EU AI Act ready.

该仓库未发布描述。

Flywheel runs AI tasks with a model you choose and keeps a receipt anyone can recheck offline.

Generate PDFs from JSON — declarative, serverless, no Chromium. TypeScript-first with professional typography.

Find, explain, and safely fix bad data. Local-first data quality for files, databases, CI pipelines, and AI agents.

TrainingPeaks MCP server for Claude Desktop, Code and Cowork. No API approval needed - works with any account. Query workouts, CTL/ATL/TSB fitness data, power PRs via natural language.

Modular Ruby framework: distributed async job engine with optional LLM gateway, MCP server, and RBAC. Zero-infrastructure lite mode. No feature gates.

Claude code memory, or maybe not code.

Cross-agent permission policy for AI coding agents. MCP sync daemon, CLI, codecs, and evaluator. One .agents/permissions.json for every agent.

Self-hosted AI agent for automation, messaging, tools, integrations, and device control.