Starred repositories
MCP server and Claude Code skill for Excalidraw — programmatic canvas toolkit to create, edit, and export diagrams via AI agents with real-time canvas sync.
OpenBao is a software solution to manage, store, and distribute sensitive data including secrets, certificates, and keys.
The official Go SDK for Model Context Protocol servers and clients. Maintained in collaboration with Google.
AgentENV (AENV) is a distributed platform for running agent environments at scale.
shadcn-style components for gsx — copy-in, type-checked, server-rendered
The fastest, litest AI Gateway. Rust core with Python SDK. Call 100+ LLM APIs in OpenAI (or native) format with cost tracking, guardrails, load balancing, and logging [Bedrock, Azure, OpenAI, Anthr…
Fastest enterprise AI gateway (50x faster than LiteLLM) with adaptive load balancer, cluster mode, guardrails, 1000+ models support & <100 µs overhead at 5k RPS.
Next Generation Agentic Proxy for AI Agents and MCP servers
Build your own AI SRE agents. The open source toolkit for the AI era.
A Docker-powered RAG system that understands the difference between code and prose. Ingest your codebase and documentation, then query them with full privacy and zero configuration.
Generic multi-tenant JWT/OIDC auth gateway fronting any streamable-HTTP MCP server (e.g. github-mcp-server, mcp-grafana) with group-based tenant routing and per-tenant credential injection.
The open-source context layer for your AI. Catalog your tables, topics, queues and APIs then expose real metadata to your AI agents.
Fast, lossless LLM inference via dual-view diffusion decoding.
The open source control plane for AI inference
Operator to streamline renovate executions in Kubernetes
Shadow any website for offline viewing, with the JavaScript stripped out
OIDC authentication and authorization termination for Caddy
MCP Auth Proxy is a secure OAuth 2.1 authentication proxy for Model Context Protocol (MCP) servers
Compress tool outputs, logs, files, and RAG chunks before they reach the LLM. 20% fewer tokens for coding agents, 60-95% fewer tokens for JSON, same answers. Library, proxy, MCP server.
Hindsight: Agent Memory That Learns
DeepSeek-native AI coding agent for your terminal. Engineered around prefix-cache stability — leave it running.
A Python framework for self-hosted LLM tool-calling and multi-step agentic workflows
DeepSeek 4 Flash and PRO local inference engine for Metal, CUDA and ROCm
Go client library and CLI for interacting with Marstek Local API