Developer Tools / AI Coding Agents
Local-first coding agent that runs on the user’s machine and can work across the browser, desktop, terminal, and editor surfaces. The repo says it verifies fixes by reproducing failures and re-running assertions, with install instructions for Windows, macOS, and Linux.
The page clearly presents an AI-powered coding agent with a concrete workflow, visible usage paths, and installation guidance. It explains the product’s local/private model, its browser and desktop control, and its self-verifying repair loop, which gives enough evidence for a strong public listing.
The snapshot does not show licensing, release status, community activity, or enough hands-on examples to judge how mature the project is. It also leaves unclear which model/provider setup is required for each platform and how polished the companion apps are.
Last evaluated 31 days ago. Current rank #338. Down 4 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.
