Custom agents

Pytorch implementation of CVPR2020 paper “VectorNet: Encoding HD Maps and Agent Dynamics from Vectorized Representation”

A Minecraft coremod / Java Agent aiming to patch serious security vulnerabilities found in many different mods

Implementation of "Describe, Explain, Plan and Select: Interactive Planning with Large Language Models Enables Open-World Multi-Task Agents"

TranscriberBot for Telegram

Bringing Human Capabilities to AI Agents

Secure runtime to sandbox AI agent tasks. Run untrusted code in isolated WebAssembly environments.

Debugging skill for AI agents

Molecode presents molecules as code and enables LLMs to operate and reason on chemistry directly.

A local bridge for bidirectional collaboration between Claude Code and Codex. 连接 Claude Code 与 Codex 的本地实时协作桥接工具。

Generate editable Excalidraw diagrams from text or JSON for agents and developer workflows

[RA-Letter 2022] Reinforcement Learned Distributed Multi-Robot Navigation with Reciprocal Velocity Obstacle Shaped Rewards

The open-source SDK for creating AI plugins and actions

PostBot 3000 is an open-source project that shows how to build a powerful AI agent and stream responses and generate artifacts. This project makes it easier for anyone looking to implement similar solutions.

FireAct: Toward Language Agent Fine-tuning

An agent-based simulation of corona and other viruses in python

Nova-Proximity is a MCP and Agent Skills security scanner powered with NOVA

The NodeQuery agent collects selected linux server data and sends them to our monitoring system for further processing.

MagicSkills：Stop copying skills between agents. MagicSkills turns scattered SKILL.md folders into reusable, composable, tool-ready capabilities.

A suite of Rust CLI tools for agentic trading and market intelligence. Each exchange has its own dedicated binary — hyperliquid, binance, coinbase, okx, polymarket — plus a shared fintool for exchange-agnostic market intelligence (quotes, news, SEC filings). Supports crypto, stocks, commodities, and prediction markets.

Official Repository of paper VideoGPT+: Integrating Image and Video Encoders for Enhanced Video Understanding

AI auto-completion plugin for Monaco Editor, inspired by GitHub Copilot.

A local-first, encrypted Slack/Discord alternative built for the agentic era. AI agents, such as openclaw, join channels, receive tasks, and coordinate on equal footing with humans — over a serverless P2P mesh.

Achieve arbitrary kernel read/writes/function calling in Hypervisor-Protected Code Integrity (HVCI) protected environments calling without admin permissions or kernel drivers.

Lightweight, high-performance cross-platform desktop app to browse, sync, and manage AI agent skills across Claude Code, Cursor, Gemini CLI, Copilot, and more.（轻量高性能的跨平台 AI Agent Skills 管理工具）

An Agent Skill focused on Apple’s Core Data framework, helping with data modeling, fetch requests, performance, and common persistence patterns.

Survey and paper list on efficiency-guided LLM agents (memory, tool use, planning).

Agentic World Modeling: Foundations, Capabilities, Laws, and Beyond

Character Animation Creator Skill for Codex and GPT Web Agent — generates game-ready animations and sprites from reference images or text prompts

🧬 Symbio（共生）- AI Infra 级多 Agent 协同框架 | 33 Killer Features: 动态 DAG, 本体化记忆, 防过早完成, 数据飞轮, 神经符号安全, OpenTelemetry 可观测, HITL 人类介入, MCP 原生支持, 语义缓存, PromptOps, 边缘计算, 隐私计算 | Next-Gen AI Infrastructure for Multi-Agent Orchestration

Put the world's smartest AI agents & plugins in your pocket

Postman MCP Server — connect AI agents (Claude Code, Cursor, VS Code Copilot, Gemini CLI) to your Postman collections, OpenAPI specs, and environments via Model Context Protocol (MCP)

Standalone agent runtime core with neutral LLM types, provider clients, tool loop, and extension protocols.

An infinite canvas for learning — select text, ask, and answers branch out as documents. MCP server for Claude Code, Codex, and any agent.

The AI agent that interacts with you in the real world.

Firefox Voice is an experiment in a voice-controlled web user agent

A CLI for library maintainers to generate, validate, and ship Agent Skills alongside their npm packages.

Hulken is a stress testing tool for everything speaking HTTP. Hulken supports multiple urls, GETs and POSTs, static and dynamic payloads, multiple agents and more. Hulken is highly configurable but defaults to some reasonable settings. Hulken works both as a library and a stand-alone command line tool. Hulken is swedish for The Hulk.

function calling-based LLM agents

META‑AGENTIC α‑AGI 👁️✨ — Mission 🎯 End‑to‑end: Identify 🔍 → Out‑Learn 📚 → Out‑Think 🧠 → Out‑Design 🎨 → Out‑Strategise ♟️ → Out‑Execute ⚡

AI-native data platform: 60+ connectors, dlt-based ETL, DAG scheduling, per-source RAG knowledge bases, and sandboxed AI agents that query, chart, and analyze your data.

SRE reliability instrumentation for agentic AI — DQR, TIE, HER, AQD

Measuring agents' ability to get work done on a computer

Private voice keyboard, agent, AI chat, images, webcam, recordings, voice control with >= 4 GiB of VRAM.

StatsPAI is the first Agent-native Python library for causal inference and applied econometrics — unified API, broad cross-method coverage, structured result objects, machine-readable schemas, Skills, an MCP server, and R/Stata parity validation.

On-demand Linux computers you can hand to an AI — real Firecracker microVMs with a browser, terminal, coding agents, and an AI that drives them.

Agentic RAG for any scenario. Customize sources, depth, and width

KEras Reinforcement Learning gYM agents

An auto-documenting, model-agnostic AI workflow for any project, framework, and language. It reduces hallucination and keeps delivery predictable: the developer controls the path, AI executes the steps, and project standards stay consistent.

llmbasedos — Local-First OS Where Your AI Agents Wake Up and Work

Chat Quality Agent - Agent phân tích chất lượng CSKH bằng AI

Exploring the Model Context Protocol (MCP) through practical guides, clients, and servers I've built while learning about this new protocol.

Typed control surface for Unreal Engine that lets AI agents introspect assets, author Blueprints/AnimBPs, and edit levels — with reactive events and undoable writes.

Open-source memory runtime for AI agents — reproducible, provenance-tagged context bundles instead of query-time retrieval. Apache-2.0, self-hosted on Postgres + pgvector, Python + TypeScript SDKs.

A self-hosted AI assistant for academic research — manages your papers, searches literature, tracks deadlines, and answers you on the channels you already use.

An autonomous AI agent pipeline for rigorous academic research, featuring strict DOI verification, multi-agent Scopus/OpenAlex/Semantic Scholar retrieval, and APA 7th .docx generation

Open-source framework to drive a real phone with AI agents: Android over ADB, iPhone over WebDriverAgent, 62 MCP tools, Python skills, a Vue dashboard, and swappable local or cloud LLMs

Main rossoctl repo - installer, UI and docs

Pharos — local-first agentic RAG for your team's document library: multi-format ingest, hybrid retrieval, enterprise ACL, dual HTTP + MCP exits.

An agentic skills framework & bundle-plugin engineering toolkit that works.

A General, Accurate, Long-Horizon, and Efficient Mobile Agent driven by Multimodal Foundation Models

Xircuits toolkit for creating and experimenting with BabyAGI/AutoGPT-style agents

MoFA - Modular Framework for Agents. Modular, Compositional and Programmable.

AI-powered login automation. Uses Claude to classify login pages and Playwright to interact with them.

Multiplatform Client for ChatGPT using SwiftUI, support iOS, iPadOS & MacOS

better git cli for agents

[NeurIPS 2024] ReEvo: Large Language Models as Hyper-Heuristics with Reflective Evolution

Token-efficient autonomous task execution with context collapse for pi coding agent

Official Model Studio CLI（阿里云百炼 CLI）built for AI Agent frameworks, exposing models, search, multimodal, and workflow capabilities as structured tool calls.

The Finn-loop: a 3-skill AI software factory for Claude Code — spec, build, review. Humans merge.

AI-assisted development for the Godot engine.

Opensource Memory for Agents

C2S Agent is an lightweight AI Agent construction platform that provides configurable online Agents and MCP services, You can configure any HTTP request interface as an MCP tool. C2S Agent 是一个轻量级的AI Agent构建平台，提供在线可配置的Agent，MCP，您可以一个HTTP请求的接口配置成为一个MCP工具，Agent之间可以进行自交流。并提供了单端口多A2A服务，MCP服务的解决方案

Voice-activated AI assistant with speech recognition and NLP. Automate tasks effortlessly with this Jarvis-like personal assistant.

Open-source AI real estate search with RAG, vector search, multi-provider LLMs, FastAPI, Next.js, ChromaDB, and a live demo.

The semantic layer that makes enterprise data understandable to AI agents — model entities and relations once, query through SPL/MCP/REST, and connect telemetry, services, and business objects in one object graph.

Local-first, multi-agent skill governance and Sublation workflow (v4.0).

Programmatic memory for long-horizon LLM agents: the harness appends everything to one log, and the agent searches it with code. 97.4% on ARC-AGI-3 (arXiv:2607.20064)

Self-improving agent runtime that learns from experience — test-verify-fix loops, correction detection, cross-project memory, multi-model orchestration.

Find best-response to a fixed policy in multi-agent RL

DEPRICATED! Use the multi-agent suite instead!

Lightweight agent orchestration dev tool that lives in your repo

[NeurIPS'25, ICLR'26] Graph Foundation Model for Retrieval Augmented Generation

2000+ free N8N AI automation workflows. Discover, copy and use in your projects.

Foam-Agent: An end-to-end, composable multi-agent framework for automating CFD simulations in OpenFOAM. NeurIPS 2025 Machine Learning and the Physical Sciences Workshop.

RL environments + evals for AI agents. Define once, train anything.

A python wrapper for the Doc2X API and comes with native texts processing (to improve PDF recall in RAG). | Doc2X API的python封装，同时附带本地的文本处理(提升PDF在RAG中的召回率)。

🔐 Firewall Your Data, Control Agents. Prevent agent data exfiltration. Gain visibility into AI's interactions with your data / systems of record / existing software. https://discord.gg/tXjATaKgTV

Official code for article "LLMLight: Large Language Models as Traffic Signal Control Agents".

Optimization Modeling Using mip Solvers and large language models

[USENIX Security 2025] PoisonedRAG: Knowledge Corruption Attacks to Retrieval-Augmented Generation of Large Language Models

🔍 Source code leak? Production code? 13 chapters breaking down Claude Code's production-grade architecture layer by layer — the most visual + agent simulator + source code analysis

Local-first persistent memory for AI coding agents (Claude Code, Cursor, Codex) over MCP. Decisions, lessons and facts live in one SQLite file on your disk. Offline, multilingual.

ToolQA, a new dataset to evaluate the capabilities of LLMs in answering challenging questions with external tools. It offers two levels (easy/hard) across eight real-life scenarios.

OpenClaw Android Setup Guide Transform any old Android device into a 24/7 AI agent running locally. This guide provides step-by-step instructions for installing and running OpenClaw on Android using Termux and Ubuntu (proot), no PC or cloud server required. What You'll Get Fully local AI agent running on Android 10+ Web-based dashboard accessible

Record and Replay AI Agent Trajectories.

From thought to skill. From signal to structure.

The universal skill manager for AI coding agents.

AI EDR for developer workstations and autonomous agent fleets. Build Swarm Detection & Response platforms with Clawdstrike.

Sandboxed AI agent orchestration platform

Agentic malware analysis environment with MCP-connected disassemblers, RE tooling, and structured workflows for Claude Code and Codex CLI.