A benchmark comparing eight AI agent harnesses running the same Kimi K3 model across 25 business-application tasks. It compares pass rates, speed, tool calls, token usage, and estimated cost, finding substantial differences between harnesses.
A controlled benchmark comparing eight agent harnesses—Oh My Pi, Kimi Code, Hermes Agent, Claude Code, Pi Agent, OpenCode, Grok Build, and Codex—using the same Kimi K3 model via OpenRouter, identical tools, and 25 complex business-app tasks. Results show a 20-point pass-rate spread, major differences in speed and cost, and that more tool calls did not guarantee better outcomes.
Self-hosted AI gateway routing across 268 providers with auto-fallback, token compression (RTK+Caveman), built-in MCP server, and cloud agent support. 33k+ stars, MIT license.
Self-hosted AI router with 3-tier auto-fallback (subscription → cheap → free) across 60+ providers. RTK+Caveman token compression saves 20-65%. One OpenAI-compatible endpoint for all CLI tools. MIT license.
Self-hosted radio station powered by LLMs — generates segments, picks music, and delivers DJ banter autonomously.
Create beautiful slides on the web using a coding agent’s frontend skills
A tool that uses LLMs and vision-based OCR to process and digitalize documents in paperless-ngx, enabling AI-assisted tagging, categorization, and data extraction. A self-hosted, Docker-deployable add-on for the paperless document management stack.