34 packages found
The RL Bridge for LLM-based Agent Applications. Made Simple & Flexible.
Asynchronous LLM Agent playing games of Mafia against human players
DistRL: An Asynchronous Distributed Reinforcement Learning Framework for On-Device Control Agents
Framework and toolkits for building and evaluating collaborative agents that can work together with humans.
A repo lists papers related to LLM based agent
[Up-to-date] A curated list of resources on graph-empowered agents and agent-facilitated graph learning (Graphs Meet Age
This is the public release of MIRA OS. Discrete memories decay through momentum loss, tools auto-configure when dropped
🤖 A composable framework for building AI applications.
An experimental game engine for robots (and their humans), made by robots (and their humans)
A Python-based framework for building multi-agent systems with LLMs. Currently in pre-launch alpha.
Your easy to use, always-on AI workforce 👾
Intelligent data acquisition framework for GitHub and web sources
Voynich Manuscript Decoded: Elu-Sinhala Phonetic Transcription & Vocabulary Toolkit 2026
A collection of Summoner clients and agents featuring example implementations and reusable templates
scAgent: No-code single-cell analysis for every biologist
💻 A curated list of papers and resources for multi-modal Graphical User Interface (GUI) agents.
RLAnything (ICML 2026) & AutoTool (ICML 2026), DemyAgent: Open-Source RL for LLMs and Agentic Scenarios
🗜️ Codebase-digest is your AI-friendly codebase packer and analyzer. Features 60+ coding prompts and generates structur
pebkac Chrome Nonautomation - A Local LLM-Driven Web Co-Browser using Smolagents, Zendriver, Trafilatura.
PHP SDK for Claude - Provides complete 1-for-1 functionality of the Official Python SDK
Automatic context preservation for Claude Code. Never lose work to compaction again. 7 hooks, 187 semantic patterns, 3 M
GoClaw - GoClaw is OpenClaw rebuilt in Go — with multi-tenant isolation, 5-layer security, and native concurrency. Deplo
AWS AI Stack – A ready-to-use, full-stack boilerplate project for building serverless AI applications on AWS
A transparent, minimal, and hackable agent framework. ~300 lines of readable code. Full control, no magic.
🏛️ Hermes Gate — Terminal TUI for managing remote Hermes Agent sessions with auto-reconnect, detach support, and zero c
See your AI agents work. Real-time 3D visualization of Claude Code activity, multi-agent orchestration, and REST API int
A CLI/TUI app that orchestrates multi-agent conversations by enabling different AI CLI tools (Claude Code, Gemini, Qwen,
A CLI tool that leverages AI (Claude Code CLI or OpenAI API) to automatically review pull requests across GitHub and Azu
Connect RStudio to Claude Code, Codex, Gemini, and other LLM agents via MCP. Multi-agent orchestration, automated manusc
A High-Availability, Transparent, and Smart Multi-Vendor Proxy for Claude Code. Support Claude Plans, GitHub Copilot, Go
A multi-user LLM agent whose knowledge, skills, and tools live in the database — grows at runtime, no redeploys. Web cha