Starred repositories
Camelid: a Rust-native local inference backend with evidence-gated model compatibility.
Lynn: open-source desktop/CLI AI Agent with GUI Session Map, headless workers, realtime voice, long-term memory, Brain V2 routing, local 27B/35B GGUF support, and contract-based Agent Regression Kit.
poolsideai / llama.cpp
Forked from ggml-org/llama.cppLLM inference in C/C++
A SQL database in Rust: SQLite-compatible, now also speaking Postgres (experimental). The LLVM of databases.
Real-time global intelligence dashboard. AI-powered news aggregation, geopolitical monitoring, and infrastructure tracking in a unified situational awareness interface
《深入理解 AI Agent：设计原理与工程实践》（李博杰 著）开源主仓库：全书正文、编译版 PDF 与按章配套代码
ciru-ai / ROCmFPX
Forked from charlie12345/ROCmFPXROCmFPX Family for AMD Hardware and Processors. More quants and special agent quants
A tool for creating and running Linux containers using lightweight virtual machines on a Mac. It is written in Swift, and optimized for Apple silicon.
Phistory automatically archives versioned system prompt snapshots from agent CLIs like Claude Code, Codex, OpenClaw, and Hermes.
Intercept and inspect Coding Agent API traffic from Claude Code, Codex CLI, Gemini CLI, Cursor CLI, OpenCode, Kimi/Kimi Code, Pi, and Hermes in a local trace viewer.
Context window optimization for AI coding agents. Sandboxes tool output (98% reduction), persists session memory, and enforces routing across 17 platforms via MCP + hooks.
High-performance AI coding agent CLI written in Rust with zero unsafe code
Pi extension for async subagent delegation with truncation, artifacts, and session sharing
High-performance code intelligence MCP server. Indexes codebases into a persistent knowledge graph — average repo in milliseconds. 158 languages, sub-ms queries, 99% fewer tokens. Single static bin…
High-performance code intelligence MCP server. Indexes codebases into a persistent knowledge graph — average repo in milliseconds. 158 languages, sub-ms queries, 99% fewer tokens. Single static bin…
ROCmFPX Family for AMD Hardware and Processors. More quants and special agent quants
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.
MCP server for interfacing with Godot game engine. Provides tools for launching the editor, running projects, and capturing debug output.
AI chat and agent tooling for Godot, with both MCP support and in-built native chat window.
⌥ AI Coding agent for the terminal — hash-anchored edits, optimized tool harness, LSP, Python, browser, subagents, and more
SkillOpt is a text-space optimizer that trains reusable natural-language skills for frozen LLM agents through trajectory-driven edits, validation-gated updates, and deployable best_skill.md artifacts.
OpenAI-compatible proxy that stacks the free tiers of 28 LLM providers (~4B tokens/month) behind one /v1 endpoint — plus any custom OpenAI-compatible endpoint. Smart routing, automatic failover, en…
Comet: agent skill harness for turning ideas into evaluated workflows
Demonstration and Template Projects