Developer Tools / AI Agents
Open-source agent harness that starts from a tiny loop, gives the model one exec tool, and stores the agent’s state and sessions inside its own directory. It includes setup commands, model configuration notes, and design rationale.
The page clearly describes an AI agent project with concrete runtime behavior, installation/startup commands, model configuration, and a documented design. It is specific enough for a useful public listing and shows how the harness works, how to launch it, and where the agent stores its evolving state.
The snapshot does not show the full implementation details of seed.py, the contents of the design doc, or how reliable the self-modifying loop is in practice. It also does not show test coverage, releases, or maintenance activity beyond recent commits and repo metadata.
Last evaluated 11 days ago. Current rank #1173. Down 2 spots in the rankings.
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.
Traccia is an AI agent observability and governance platform with OpenTelemetry-native tracing, runtime policy enforcement, prompt registry, evals, cost attribution, and compliance evidence export.
Single-binary CLI that builds an AI agent knowledge base from git repos, Claude Code/Codex sessions, and saved links. It generates a portable markdown wiki, runs on cron, supports local Ollama mode, and exposes the result for agents via CLAUDE.md/AGENTS.md and MCP.
A lightweight React Markdown renderer with built-in LaTeX, syntax highlighting, streaming-safe rendering, and security-focused defaults.
