repository

CodeGraph is a local code knowledge graph for AI coding agents like Claude Code, Cursor, Codex, OpenCode, and Hermes Agent. It aims to cut token use, tool calls, and runtime by letting agents query pre-indexed code structure instead of scanning files repeatedly.

AI code review tool that scores code against six decay-risk dimensions inspired by twelve classic engineering books, with book citations, severity labels, and remediation guidance.

AirLLM is an open-source inference library that aims to run very large language models on small GPUs by decomposing models layer-wise and streaming them during execution. The snapshot shows a detailed README with quickstart code, model examples, supported model notes, and recent update history.

A Claude Code skill that lets the model inspect live camera frames so it can verify hardware displays, spot wiring issues, and check physical UI behavior on real devices.

Headroom is an open-source context compression layer for AI agents. It compresses tool outputs, logs, files, RAG chunks, and conversation history before they reach the LLM, with support for a library, proxy, and MCP server.

Looma is a local-first Python CLI that turns coding-agent history into resumable project context. It reconstructs work items, decisions, blockers, linked commits, and next steps from Claude Code, Codex, and Cursor sessions, with optional local LLM extraction and no cloud or API keys.

Dex is an agent-native analytics engineering toolkit for working with warehouses and dbt projects. It supports exploration, dbt transformation, semantic modeling, and schema-drift maintenance, with installs for Claude Code and other agents.

Local code-context engine for AI coding agents. It indexes TypeScript, Python, or Swift repositories into a symbol-level graph in SQLite and exposes MCP tools for symbol lookup, impact analysis, and graph queries.

Persistent memory for AI agents that retires superseded facts instead of letting old and new information conflict. The repo shows quick start setup, MCP connections for several agent hosts, and benchmark claims for retrieval accuracy.

Mindlas is a local-first tool for monitoring Claude Code sessions and catching agent drift before bad code lands. It offers deterministic gauges, live session tracking, correction commands, and install paths for both a plugin and PyPI/CLI use.

CLI for maintaining agent-edited Markdown wikis and indexed knowledge bases, with commands for initializing, syncing, linting, searching, and reading wiki content.

An open-source CLI for orchestrating long-running coding agents from a single terminal, with phases for research, planning, implementation, review, and PR creation.

A persistent code knowledge graph and MCP server for AI coding agents. It analyzes codebases, builds a graph of files, symbols, commits, and cross-boundary edges, and exposes MCP tools plus generated markdown artifacts for agent workflows.

A Go-based local orchestration platform for AI coding agents, with live event streaming, session replay, and durable execution history.

A TypeScript CLI and SDK for testing whether Agent Skills improve model outputs by running with-skill vs baseline evaluations and generating reports.

Orbit is a multi-repo Git workspace tool for coding agents. It uses real worktrees and full git history so an agent can read, modify, and commit across several repositories in one unified workspace, with support for Claude Code, Codex, OpenCode, and Qoder.

A CLI for searching local agent session history and tracing code changes back to the sessions that produced them.

NoWreck is a CLI verifier that checks whether AI coding assistant claims match the actual code changes using structural analysis rather than another model judgment.

Hubo is a coding-agent workflow that uses two persistent roles — a work agent and a review agent — to iterate on code changes until review findings are resolved or a human decision is needed. The repo includes installation steps and usage examples for Claude Code, Codex, GitHub Copilot CLI, OpenClaw, and skills.sh.

Sentinel is a local, zero-dependency codebase scanner that maps a repository into AI-ready context, health scores, risk hotspots, entry points, and prompts for coding agents.

Spewer is a local service for delegating bounded coding tasks to cheaper models, with durable task state and evidence-rich receipts. The repo shows install, ask, background task, watch, check, and cancel flows, plus local Ollama/Qwen3 support.

Open-source agent skill and Python service for stripping AI provenance marks from text and files. It supports multiple hosts, includes install scripts, hooks, and a service-backed workflow for cleaning watermarks across many file types.

Open-source repository for a NanoGPT training speedrun, focused on getting a 124M model to target loss on 8x H100 GPUs in under 90 seconds. The README includes run commands, Docker instructions, and a detailed list of model and systems optimizations.

Deterministic retrieval-only Q&A system for documentation that avoids LLM calls at runtime. It uses Gemini embeddings, local Qdrant storage, and a CLI chatbot to answer questions with low latency and near-zero per-query cost.