Custom agents

Simple GPT reference agent for Crustocean

Analyzer: called is a analyzer which can find function calling

Automates steady and unsteady adjoints (general solvers and ODEs respectively). Forward and reverse mode algorithmic differentiation around implicit functions (not propagating AD through), as well as custom rules to allow for mixed-mode AD or calling external (non-AD compatible) functions within an AD chain.

chatbot framework that allows for the creation of highly customized models using structured prompts against the base text-davinci models... extends context window via summarization. Donate if you want to see this on GPT-4

An Agentic RAG starter that use Swarm, Nemo Guardrails and SingleStore as a database

A collection of AI related python scripts for things like training, RAG and agents.

Framework for Self-Organizing Python Agents

Framework for building AI agents with real-time adaptive learning capabilities.

Beyond chatbots: an AI platform that understands user intent and dynamically renders contextual UIs. 1,100+ tools, 30+ models, 100+ integrations.

🚀 A collection of Claude subagents, skills, rules, guides, and blueprints for Developers, Engineers, and Creators. | Covering programming languages, DevOps, Cloud, and beyond.

Production-ready AI infrastructure: RAG with smart reindexing, persistent memory, browser automation, and MCP integration. Stop rebuilding tools for every AI project.

An Agent-native Obsidian wiki + CLAUDE.md skeleton that lets Agent know your project as well as you do.

This is the repo for the team Pikachu's solution in the League of Robot Competition 2023. Our solution won the Overall Best and Fast Mover tracks and ranked second in the Line Honours track.

Open DeepResearch is an application for assisting in research by conducting comprehensive research on any topic.

A repo listing known open source voice tools, ordered by where they sit in the voice stack

Data-Driven Cycling using Strava data and GPX data analysis. Digital Personal Trainer using old cycling workout data to predict new workouts

用于企业微信自建应用的机器人代码库，实现消息回复、消息推送等功能。

Query Only Linear Adapter Training for Fine Tuned Embedding Model Query Representation

[ACL'25 Main] SelfElicit: Your Language Model Secretly Knows Where is the Relevant Evidence! | 让你的LLM更好地利用上下文文档：一个基于注意力的简单方案

mkenv is a fast, secure, reproducible local isolated development environment generator.

Code for the OpenCV demo of a recipe transcription OCR agent.

(ACL2025 Findings) Official code for the paper "STeCa: Step-level Trajectory Calibration for LLM Agent Learning"

学习日志记录/笔记，涉及 LLM，AI Agent，客户端、前端、后端等相关领域技能知识

Create your own autonomous agent to help with the development of Godot Engine games.

Decision Transformer for offline single-agent autonomous highway driving

A production-ready starter kit for building AI agents and multi-agent swarms on NEAR.

Multi agent PPO implementation in Pytorch for Unity ML Agents environments.

Texas Poker Multi-Agent Game/多智能体德州扑克游戏

An inverse game solver for inferring objectives from noise-corrupted partial state observations of non-cooperative multi-agent interactions.

(Official) PyTorch implementation for Trajectory-Class-Aware Multi-Agent Reinforcement Learning (ICLR 2025)

Self-Adaptive_Swarm_System(SASS) for 2019 IEEE International Symposium on Multi-Robot and Multi-Agent Systems (MRS) Version. Paper: Self-Reactive Planning of Multi-Robots with Dynamic Task Assignments

A specialized framework for Model Context Protocol (MCP) development featuring 8 Claude Code sub-agents, security hooks, and production-ready FastMCP server templates. Provides immediate MCP development assistance through markdown-driven agents with optional programmatic SDK .

Provides `soracom` command, a command line tool for calling SORACOM APIs. SORACOM API を呼び出すためのコマンドラインツール soracom を提供します。

Decision-tree backed chatbot framework.

Agentic RAG system grounded in Ethereum specs, discussions, papers, and codebases

A software framework for building AI agents through composition.

Turn-based strategy game / agent-based simulation framework / social model in 4D relativistic spacetime

TypeScript framework to build robust, agent-ready MCP servers around your APIs.

A functional, Effect-TS-based AI coding assistant CLI with multi-provider support.

A small operating file for keeping long-running AI agent sessions from degrading. Capable models can do useful long work. The problem is not usually raw intelligence. The problem is operational drift: Stops AI coding agents from rotting during long sessions. One file, MIT licensed.

Autonomous Polymarket scanner — Claude finds mispriced probabilities, Kelly sizes the edge

Simple LLM agent that just use bash to do all the jobs

An advanced Self-Centered Intelligence (SCI) prototype that represents a new paradigm in AI-human interaction.

本仓库旨在记录和分享我在 LLM 和 Agent 领域的学习历程，并通过实践项目深入理解相关技术。通过从零开始构建基于 LLM 和 Agent 的应用，学习LLM原理和Agent开发经验。

Benchmark of local LLM models for agentic-coding daily tasks.

This is a software which can by used by researcher multi-agent reinforcement learning in robot learning for multi-robot system

一个极简的 Go HTTP 网关服务，将 HTTP 请求桥接到 Claude CLI。通过 HTTP 接口调用 Claude CLI 的无头模式，让任何支持 HTTP 的应用都能使用 Claude CLI 的能力。

Feishu/Lark group chats connected to Claude Code agents. Per-group isolated sessions, streaming card responses, deep Feishu integration.

Claude Code skill: Generate file-by-file code tutorial websites for any repository with parallel agent teams

A repository for a Java implementation of AutoGPT. It is heavily inspired by AutoGPT if not a clone of some of its functionality, though there is some deviation from it particularly in how Agents are implemented as well as planned support for more open source models.

Controllable reasoning demos for NVIDIA Nemotron 3 Super (120B/12B MoE) — chat UI, CLI, API server, tool calling, budget sweep, and adaptive routing

Reactor is named after Iron Man's arc reactor. It is not a single tool, but the core energy source that keeps an AI Agent running. For one-person companies and indie builders, Reactor is the AI agent reactor for building products

Just mention want you want and it will extract/scrape data from the Web. Useful to create AI web search+extraction/scraping agent, RAG with web data etc.

Java Agent Based Modelling toolkit

MCP server for building Teal R Shiny apps with AI assistance. Clinical trial data analysis made easy with Claude, Copilot & more.

An AI personal assistant done the right way.

Wallet-as-a-Service for all AI agents in the world

Deep research agent using Amazon Bedrock, AgentCore, and LangGraph

🍺 AI-powered Oktoberfest reservation agent — monitors 38 beer tent portals, sends push alerts when evening slots open, and helps you book via chat. Web dashboard + MCP server + CLI.

AI HR Agent for HRMS

MCP server for hive-framework development. A memory and agentic coordination solution.

Global, unlimited persistent memory for Claude Code agents. Context-activated hints injected automatically via hooks using scatter-gather map-reduce.

Full-stack air quality analytics platform built with FastAPI, React, and MySQL. Aggregates multi-source PM2.5/PM10 data, performs multi-city comparison and time-series forecasting (SARIMAX), and integrates an LLM-based planning agent with tiered access, secure APIs, and PDF reporting.

AI-powered deep research tool leveraging web scraping for cost-effective, comprehensive analysis. Open-source and API-cost free!

NotebookLM on steroids — purpose-built for security researchers.

A study assistant powered by Claude Opus. It provides various tools to assist with different tasks, such as researching,coding,note-taking and more.

a complete RAG-Ready fast api app for your Rag Systems

MCP tools to connect LLMs and ABACUS jobs

Open source multi-agent platform. Deploy autonomous AI coding agents to WhatsApp, Slack, Telegram, and Discord.

Conversational Music Recommendation with LLM Tool Calling

AI SDK for Go: Build production-ready AI apps with a unified API for text generation, structured output, streaming, tool calling, and agentic workflows. Built by Google.

七天从零实现一个Claude Code。 Complete a Claude code from scratch in seven days.

Search, preview, and analyze datasets from 20+ platforms via a single MCP connector. Works with Claude instantly.

[NeurIPS 2025] TrajAgent: An LLM-Agent Framework for Trajectory Modeling via Large-and-Small Model Collaboration

AI coding agent in C. Single binary, zero runtime deps, every major LLM provider.

Benchmarking LLMs and Agents in Rigorous Financial Analysis and Forecast

Lily Protocol is an on-chain financial infrastructure built on the Stellar network that enables AI agents (AgentLily) to own wallets, hold USDC, execute payments, and transact autonomously.

A lightweight, production-ready multi-agent framework

A multi-model AI council CLI that provides consensus-driven decisions using Claude, Codex, and Gemini.

Nature and nurture combined adapt faster than either alone. Darwinian evolution (agents selected across generations) plus Multi-Agent Deep RL (agents learning within a lifetime) in one ecosystem, each mechanism amplifying the other — a testbed for the Baldwin effect, coevolution, and emerging cooperation.

Berkeley Function Calling Leaderboard (BFCL) with Chinese-Language Evaluation

🎓 StudySync is a productivity app with tools like AI-powered study tips, music recommendations, a Pomodoro timer, and more to help enhance your study routine and stay organized. Welcome to a suite of tools designed to boost your study & productivity!

📚 Comprehensive collection of notes and resources from Generative AI courses covering LLMs, prompt engineering, RAG, AI agents, and more

A curated list of Offensive Security MCP Servers for Red Teaming & Pentesting.

AI superpowers you own. Sila is an open alternative to ChatGPT where you own AI assistants, chats and data.

A deep research assistant based on the Langgraph4j framework with iterative deep research capabilities. 基于 Langgraph4j 框架的深度研究助手，具备迭代式深度研究能力。

A curated list of Artificial Intelligence Top Tools. With repository stars⭐ and forks🍴

AI-Suite - n8n, OpenClaw, Open WebUI, OpenCode, Llama.cpp/Ollama, Flowise, Langfuse, MCP Gateway and more!

Open-source bundle of agent methodologies and Hermes-compatible skills.

AI Agents internals - system prompts, tool architectures, and implementation patterns

Browser-native agent · profiles · tools — by aratech | Zero installs, isolated, secured and self-evolving agent.

Knowledge-base-driven article generation, fact audit, and 7-platform publish packs for WeChat, Xiaohongshu, Zhihu, Juejin, CSDN, Toutiao, and Weibo, with Wechatsync draft-sync handoff.

A GUI for Claude Code and Codex, built for multi-agent orchestration — with 'superthink' adversarial verification, agent memory, and Discord remote access

Infrastructure Context for your Coding Agents (Claude Code / Cursor)

Local-first Python CLI and MCP server for versioned, cited context from web and document sources.

Browser-first text exploration, clustering, and grounded RAG. Search, map, and analyze private documents locally with zero cloud uploads - all powered by WebGPU, UMAP, and local LLMs or MCP integration.

RamiBot v3.8.0 is a local-first AI security operations platform integrating multi-LLM support, a dynamic red/blue team skill pipeline, MCP tool orchestration, Docker terminal access, Tor proxy management, and an auto-integrated Kali-based tool server (rami-kali) for controlled, extensible offensive and defensive workflows

Stock research skill for AI agents — A-share, HK, US. Plan → fetch → validate → report.