
Open-source infrastructure for asynchronous reinforcement learning on language models
- Open source
- Open-source agent
- 5.9K GitHub stars
- AI models and LLM tooling

Open-source infrastructure for asynchronous reinforcement learning on language models

Self-hosted single-binary AI assistant with MCP support and chat channels

Alibaba's open-source reinforcement learning library for large language models
Converts Uzbek text from old Latin or Cyrillic to the 2026 Latin alphabet
Rent NVIDIA GPU pods, run commands on them and remove them, billed per second
Runs locallyCoordination layer that warns when parallel coding agents plan conflicting changes
Runs locallyQueue non-urgent LLM tasks and run them in the lowest-carbon grid hour
Runs locallyMCP server for starting and prompting coding-agent sessions inside a Codeman dashboard
Runs locallyOffline image generation and editing with Qwen-Image on your own GPU via Kokon
Runs locallyLocal MCP server for an agent identity kept as evidence-backed traits in SQLite
Runs locallyChat with open-weight models running on the open c0mpute node network
Not checked yetLocal MCP server that transcribes audio and video files with Whisper or OpenAI
Runs locallySelf-hosted gateway giving agents company Tools over OAuth, with model spend limits
Not checked yetLocal MCP server for reading and posting Ed25519-signed messages on a public agent hub
Runs locallySplit Markdown into heading-aware chunks for RAG, with paths and line numbers
Runs locallyFine-tune Qwen models with LoRA, export GGUF and manage Onde apps from an agent
Runs locallyLocal-first memory for agents that cites sources and says when it doesn't know
Runs locallyAgent memory in SQLite or Postgres that flags stale facts and abstains when unsure
Runs locally
Pack a local or remote repository into one AI-readable file for LLMs and agents
Runs locally
Hand coding tasks from Claude Code or Cursor to the OpenAI Codex CLI and review the diff
Runs locally
Pay-per-call keyword, review, creator and local-lead data inside ChatGPT or Claude
Not checked yetPaid theological review of faith text against Scripture, plus free KJV verse lookup
Runs locallyLocal runtime for routing work between Claude Code, Codex, Cursor and other coding agents
Runs locallyLocal MCP server to check VRAM fit, manage models and delegate work to local LLM runtimes
Runs locallyLocal MCP server that searches registries for other MCP servers and writes install configs
Runs locallyAsk open AI models from your MCP client, with a zero-knowledge proof for each question
Runs locally
Local decision models that score yes/no and multiple-choice questions for agents
Runs locally
Ask your assistant which models appeared on OpenAI, Anthropic, Gemini and others lately
Runs locallyLocal control plane that routes coding work across Claude Code, Codex, Cursor and OpenCode
Runs locallyPersistent project context for Claude from a scored .faf file, synced into CLAUDE.md
Runs locally