114 packages found
🌱 A little course on Reinforcement Learning Environments for evaluating and training Language Models
Official Implementation of UA^{2}-Agent and other baseline algorithms of "Towards Unified Alignment Between Agents, Huma
Sotopia: an Open-ended Social Learning Environment (ICLR 2024 spotlight)
A repo lists papers related to LLM based agent
Multi-channel AI proxy with intelligent key rotation. 智能密钥轮询的多渠道 AI 代理。
[ICLR2026] The official repository for the CodeGym project: "Generalizable End-to-End Tool-Use RL with Synthetic CodeGym
Integrating OpenAI Agents SDK with Bright Data Web Unlocker, enabling AI agents to access, extract, and process structur
AIlice is a fully autonomous, general-purpose AI agent.
🔴 VERY LARGE AI TOOL LIST! 🔴 Curated list of AI Tools - Updated 2026
ALICE and its prior work, Voice2Action: Language Models as Agent for Efficient Real-Time Interaction in Virtual Reality
DistRL: An Asynchronous Distributed Reinforcement Learning Framework for On-Device Control Agents
Code and Data for "MIRAI: Evaluating LLM Agents for Event Forecasting"
Odyssey: Empowering Minecraft Agents with Open-World Skills
[Up-to-date] A curated list of resources on graph-empowered agents and agent-facilitated graph learning (Graphs Meet Age
ML-Dev-Bench is a benchmark for evaluating AI agents against various ML development tasks.
MCP Server to manage a Wordpress CMS system.
The benchmark tasks and evaluation harness for "PhysicianBench: Evaluating LLM Agents in Real-World EHR Environments".
A Comprehensive Benchmark to Evaluate LLMs as Agents (ICLR'24)
RepairAgent is an autonomous LLM-based agent for software repair.
Source code for our paper: "ARIA: Training Language Agents with Intention-Driven Reward Aggregation".
An unofficial C#/.NET SDK for accessing the Anthropic Claude API. This package is not affiliated with, endorsed by, or s
Open-source AI meeting copilot - real-time transcription, echo cancellation, and AI assistance. Captures system audio +
OpenCode plugin that uses your existing Claude Code credentials — no separate login needed.
YantrikDB memory provider for NousResearch/hermes-agent — self-maintaining memory with canonicalization, contradiction t
AI Chatbot Starter Kit: An open-source, extensible framework for rapidly developing custom AI chatbots with integrations
Towards Large Multimodal Models as Visual Foundation Agents
Easily start and manage your Claude (and Codex!) projects, including a timer!
A comprehensive and efficient MCP server for task management with multi-format support (Markdown, JSON, YAML)
Pocket Flow: Codebase to Tutorial
[ICML2025 Oral] LLM-SRBench: A New Benchmark for Scientific Equation Discovery with Large Language Models
scAgent: No-code single-cell analysis for every biologist
Prompt, run, edit, and deploy full-stack web applications. -- bolt.new -- Help Center: https://support.bolt.new/ -- Comm
Create and install AI agents to automate your tasks
[ICML 2024] LLMCompiler: An LLM Compiler for Parallel Function Calling
Pocket-sized Ruby AI agent framework / LLM assistant with multi-LLM support
AI Toolkit for Node.js (LLM, Image Generation, Embeddings, Vector Search)
Yunjue Agent: A Fully Reproducible, Zero-Start In-Situ Self-Evolving Agent System for Open-Ended Tasks
A Golang autonomous AI agent framework for assisting real work
List MCP Server configurations in your system used by AI applications like Cursor, Claude Desktop, VS Code and others
This Chatbot helps farmers make informed decisions by leveraging the power of LLM Model from OpenAI.
[ICLR 2026] Meta-RL Induces Exploration in Language Agents
A bot works with OpenAI GPT models to provide insights for your info flows.
A Systematic Survey of Deep Research
[CVPR2024 Highlight] Editable Scene Simulation for Autonomous Driving via LLM-Agent Collaboration
A fork of Anthropic Computer Use that you can run on Mac computers to give Claude and other AI models autonomous access
[ICML 2026] This is the official implementation for paper HiPER: Hierarchical Reinforcement Learning with Explicit Credi
Solana meme-coin auto-trading bot with MiniMax M2.7 LLM exit advisor, Jupiter Ultra swaps, Telegram control, and a Pepe-
irresponsible innovation. Try now at https://chat.dev/