83 packages found
ML-Dev-Bench is a benchmark for evaluating AI agents against various ML development tasks.
A custom TypeScript MCP Server intended to be used with Claude Code
"DeepCode: Open Agentic Coding (Paper2Code & Text2Web & Text2Backend)"
🔴 VERY LARGE AI TOOL LIST! 🔴 Curated list of AI Tools - Updated 2026
List of Permanent Free LLM API (API Keys)
AI Chatbot Starter Kit: An open-source, extensible framework for rapidly developing custom AI chatbots with integrations
A structural X-ray for the codebases AI agents are writing.
YantrikDB memory provider for NousResearch/hermes-agent — self-maintaining memory with canonicalization, contradiction t
A research agent system deeply rooted in your Zotero library.
Agent Interface Discovery
A repo lists papers related to LLM based agent
A powerful AI assistant integrated into KOReader.
Retrieval Augmented Generation for youtube videos with a BRAD agent
Solana meme-coin auto-trading bot with MiniMax M2.7 LLM exit advisor, Jupiter Ultra swaps, Telegram control, and a Pepe-
Route, manage, and analyze your LLM requests across multiple providers with a unified API interface.
parrot.nvim 🦜 - the plugin that brings stochastic parrots to Neovim.
Fast Obsidian-aware search and discovery that makes AI agents or OpenClaw your true knowledge assistant.
Pocket-sized Ruby AI agent framework / LLM assistant with multi-LLM support
An unofficial C#/.NET SDK for accessing the Anthropic Claude API. This package is not affiliated with, endorsed by, or s
The benchmark tasks and evaluation harness for "PhysicianBench: Evaluating LLM Agents in Real-World EHR Environments".
The RL Bridge for LLM-based Agent Applications. Made Simple & Flexible.
A Comprehensive Benchmark to Evaluate LLMs as Agents (ICLR'24)
xLAM: A Family of Large Action Models to Empower AI Agent Systems
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.
Declarative agent config for Claude Code, Codex, and Cursor: an agent.json manifest for skills, MCP servers, and stack p
Structured deep research skill for Claude Code/Open Code/Codex with human-in-the-loop control
[CVPR2024 Highlight] Editable Scene Simulation for Autonomous Driving via LLM-Agent Collaboration
[ICLR'25] OpenRCA: Can Large Language Models Locate the Root Cause of Software Failures?
DistRL: An Asynchronous Distributed Reinforcement Learning Framework for On-Device Control Agents
Your own GPT-powered Personal Assistant to whom you can ORDER or INSTRUCT to do some task or search for something using
Agentic Theorem Prover for Rocq for Program Verification
MCP Server to manage a Wordpress CMS system.
[ICML 2024] LLMCompiler: An LLM Compiler for Parallel Function Calling
[Up-to-date] A curated list of resources on graph-empowered agents and agent-facilitated graph learning (Graphs Meet Age
[🏆 CHI26 Best Paper] CoBRA: Reproducible control of LLM agent behavior via classic social science experiments
Elixir implementation of a LangChain style framework that lets Elixir projects integrate with and leverage LLMs.
Claude Code Sub Agent Manager. A simple Manager for adding Claude Code Sub Agents with hooks and custom slash commands.
Nemp - The memory plugin for Claude Code that remembers everything.
A collection of my favorite custom Claude Code resources to make life easier.
Open-source AI meeting copilot - real-time transcription, echo cancellation, and AI assistance. Captures system audio +
The open creative AI workspace
Text2Sim MCP Server is a conversational simulation engine that transforms natural language into working simulation model
Turn Webpage to LLM friendly input text. Similar to Firecrawl and Jina Reader API. Makes RAG, AI web scraping, image & w
Sotopia: an Open-ended Social Learning Environment (ICLR 2024 spotlight)
A persistent, unified memory layer for all your AI agents (e.g. Claude Code, Codex), backed by Markdown and Milvus.
This Chatbot helps farmers make informed decisions by leveraging the power of LLM Model from OpenAI.
Your agents now know when the ground shifted under their feet
Easily start and manage your Claude (and Codex!) projects, including a timer!