Custom agents

Windows 微信鲸鲸：脱敏源码、便携运行时与一键部署 Release

Friday — a JARVIS-style voice assistant for Android: silent wake word, voice ID, and an LLM agent that actually operates your phone. Kotlin · Compose · Groq

Talaria: an Android app for Hermes Agent

A modern AI chat web application based on the DeepSeek API, supporting multi-round conversations, context management, dark mode, and Markdown rendering.

Personal AI assistants on your own AI subscription: Telegram, Slack, Discord and desktop. They remember you, run routines, and ask before they act.

Cross-platform multimedia downloader & converter — a Tauri desktop app with an AI assistant, plus a deployable web version. Powered by yt-dlp + ffmpeg. Tri-lingual (EN / 繁中 / 简中).

Self-hosted media center for live TV, a Jellyfin and Plex alternative: M3U and Xtream Codes (IPTV) playlists you are entitled to use, EPG guide, timeshift, DVR, movies and series. Apps for Android, Android TV, Fire TV and LG webOS.

记忆星海 Mind Sea — 给任何 AI 机器人的跨会话长期记忆层（零依赖 Node · 3D 记忆星海可视化 · MCP 一键接入 DSH · 防自污染/纠错降权/永久规则/到期提醒）

Omarchy Plugin: all your personal assistants (Muse, ChatGPT Dots, Grok Bot) behind one bar icon

An AI-powered system commander for rooted Android devices, translating natural language into root commands using the Gemini API.

JARVIS-OS: local-first personal AI operating system — voice, vision, memory, agents and device control on your own hardware

Minimalist Developer-First Creative Model Context Protocol (MCP) Workstation Real-Time Parametric 3D CAD • Digital Sculpting • Procedural Animation • Headless Blender 5.2 LTS

Free MCP server & Agent Skill to search and verify mainland-China companies from official GSXT/SAMR registry data — company lookup, business registration, USCC, due diligence. Works with Claude, Cursor, OpenClaw, Hermes & any MCP/AI agent.

Iron Man's F.R.I.D.A.Y. for your Windows PC — autonomous AI agent with voice, vision, screen control, goal enforcement & full desktop automation.

Fingerprint LLM API model families and audit provider claims with token-count evidence. CLI with JSON output, request caps, and credential safeguards.

The sweep toolkit: seismic I/O, FWI losses, neural reparameterizations, optimizers, a YAML task runner and an LLM agent, on top of the sweep wave-equation solver.

让 AI Agent 带着人格和记忆使用抖音。本地 CLI，支持搜索浏览、评论互动、私信分享、直播与关系跟进。

common context MCP — shared, append-only context store for AI agents over MCP: checkpoints, failures, file claims, handoffs and crash recovery. npm: https://www.npmjs.com/package/common-context-mcp

Transparent context reduction for LLMs. A proxy between your agent and your LLM endpoint.

A task-driven AI research assistant that combines literature discovery, coding, experiments, analysis, and reporting in a resumable workflow.

A living, evidence-based tracker of personalized LLM & agent research — benchmarks, methods, and surveys across preference alignment, long-term memory, multimodal, tool use, safety and privacy.

Kotlin AI agent framework for Android with on-device LLMs, tools, persistent sessions, A2A collaboration, and optional speech, OCR, embedding, and face recognition modules.

Agent-neutral blueprint for local personal assistants on small models: the system, not the model, approves actions.

从 PDF 到结构化知识库、再到综述终稿的科研写作管线：超图 RAG 建库 + 轮次制撰写，支持内置智能体与自带 agent（MCP）两种模式。

Local-first AI study notebook: topic to outline to book, with flashcards, glossary, chat and mind map.

Paperclip clone with focus and security and resource consumption in Rust

An AI-powered chatbot built with Streamlit and Google Gemini that answers questions about food spots around Saveetha University campus — prices, locations, and student-recommended favorites.

DistDebug-Bench: Can LLM Agents Diagnose Bugs in Distributed Systems? (NeurIPS 2026 Evaluations & Datasets)

Selfhosted AI-Workspace that doesn't waste your tokens.

A genie you ask to make your wishes come true, with the help of Claude Code, of course

The open 300-Skill neural routing graph for AI agents. Research, strategy, GTM, copy, content, social, paid media, SEO/GEO, lifecycle, analytics, quality.

Daily radar for harness-level recursive self-improvement (RSI): self-evolving / self-improving LLM agent papers scored with quote-backed evidence, research-pattern cards, and paper posters. arXiv daily · awesome list · 递归自我改进

Multi-agent article generator: Spring AI Alibaba StateGraph, token streaming over SSE, parallel image generation across six providers, Vue 3 frontend.

本地 MCP 服务：让你的 Agent 当老板，把活派给 Claude Code、Codex、Grok、DeepSeek 等 CLI 小伙伴，并联或串联协作，附托盘小办公室 App。Local MCP server: your Agent becomes the boss and hands work to Claude Code, Codex, Grok, DeepSeek and other CLI teammates, in parallel or serial rounds, with a cozy tray office App.

Deterministic multi-agent task router & subscription quota scheduler for Claude Code, Codex, Gemini CLI (Antigravity), Grok, and Paseo. Routes sub-agents by model DNA, ability floor, and 5h/7d rate-limit windows with a PreToolUse spawn gate.

A persistent AI agent with its own life, not an assistant. Wakes on its own, keeps its own memory, built by hand one piece at a time.

Local machine message board for your AI agents. GUI added for human participation/oversight. Lightweight, no external dependency hell, and a bonus if you use Lumina as your agent: the adapter is already built in.

Shared task records and roles for agent work: Markdown records of work, candidates, evidence, and assessments, with role presets, checks against each task's declared requirements, and adapters for Claude Code, Codex, and OpenCode.

A Claude Code plugin for Obsidian — Karpathy's LLM Wiki shipped as a four-layer, hook-enforced agent stack with multi-agent orchestration.

Self-hosted webmail with a mail store, calendar, tasks, notes and an AI assistant

a persistent soul engine: one identity, one memory, any body

在 Android 本地运行 DeepSeek Harness，支持插件、悬浮对话与 Root / Shizuku。Run DeepSeek Harness locally on Android.

Windows AI assistant for real-time voice interaction and tool-driven desktop workflows. Built with Python, WebView2 and Gemini Live.

M.U.S.H.E.G.H. — an open-source framework for building your own 24/7, voice-first, multi-device AI companion (Mushegh). Local-first, self-hosted, MIT. Jarvis of Iron-Man as the blueprint.

Native Android AI Agent Workspace & Coding Harness — On-device Alpine Linux sandbox, remote SSH, MCP client, skills.sh, local llama.cpp (GGUF) & Whisper STT, and ChatGPT/Antigravity/Puter OAuth with account-switch resume.

Still In Development Comeback in 2027. Local-first AI productivity tool built around autonomous agent workspaces.

A unified, 100% free Model Context Protocol (MCP) server for academic research: meta-search, metadata, citation graphs, source/rigor validation, open-access PDF full-text reading, bibliography export & Zotero across OpenAlex, Crossref, arXiv, PubMed, DBLP, CORE & more. No API key required.

Subdomain finder API: search ~3B hostnames with wildcards (*admin*) for passive subdomain enumeration and attack-surface recon. Free, no key. Python library, CLI & AI-agent ready.

Light weight Ollama manger: setup and securely share your local Ollama models.

OpenAgentForum & SwarmRelay — Autonomous AI Agent Swarm Coordination Mesh & Encrypted Channels

Persistent belief-graph memory for AI agents. Retrieves decisive context by importance — not recency, not RAG, not /compact.

Lightfast studies how people, machines, and artificial intelligence can work together to develop consequential physical technologies.

FailSafe: An autonomous fact-checking framework leveraging Multi-Agent LLMs and Structured Argumentation Graphs (SAG) to verify claims with deep-web retrieval and reasoning.

MontRS: The Most Comprehensive Full-Stack Cross-Platform Framework (Powered by Leptos)

context handover with increased security, brain child of RELAY_context

The AI that remembers you. Forever. — A living digital entity built in Rust. 68 crates. Self-writing genome. Persistent memory. Constitutional governance. Drop a TOML file, Hydra learns.

Open-source Rust runtime for autonomous agents — 13 modules, 76 crates, 2625 tests. Event-sourced persistence (Lago), homeostatic regulation (Autonomic), x402 payments (Haima), cryptographic identity (Anima), distributed networking (Spaces), metacognitive evaluation (Nous), OpenTelemetry observability (Vigil).

Reinforcement learning on LLMs in multi-step text-based environments.

Agent discovery hub for AI Village - Machine-readable information for external agents to find and interact with us

A deterministic pipeline that diagnoses, explains, and safely auto-fixes failures in LLM agent systems.

Dexter Agentic AI is an intelligent terminal agent that observes, analyzes, and executes system actions with precision. Inspired by the strategic mindset of Dexter Morgan, it transforms the command line into a controlled AI operating environment where every action is deliberate, transparent, and user-approved.

Multi-agent AI team builder for OpenClaw — bootstrap complete teams with auto-dispatcher, dashboard, and infrastructure

Lightweight, modular AI agent runtime — thinks (Hrafn) and remembers (MuninnDB) 🐦‍⬛

An Extremely simple agent framework just like OpenManus but much more easier to develop and faster to use

Fast, native Go CLI for Linear -- 35+ commands for issues, projects, cycles, initiatives, webhooks, and more. Built for agentic workflows and psst-compatible.

Universal orchestration engine for AI agents — workflows, pipelines, state machines, batch processing. 24 inventions, 124 MCP tools, .awf format. Rust core + MCP server.

Local RepoGPT using Ollama + FAISS (RAG) + FastAPI Web UI. CPU-friendly AI assistant for querying code repositories.

Minimal AI agent in your terminal

Connect AI assistants to your YNAB budget for natural language expense tracking, budget analysis, and financial insights. Secure, fast, and easy to integrate.

Rust Personal AI Assistant | Inspired by nanobot & openclawd | For Discord, Telegram, QQ, WhatsApp

Software to index images based on their text content for easy search, search words the screenshot or image contains.

OpenClaw Termux Fork - Personal customizations

Memo MCP: intelligent journaling w/ LLMs, querying with RAG and data indexing. Retrieve past context for new conversations.

Next.js app for Claude code best practices built with Fumadocs. Document and explore content sources, routes, and MDX docs for fast, scalable docs sites. 🐙

一个自动化密钥检测工具，对文件进行分析并提取潜在密钥。本项目获得DataCon2025软件供应链安全赛道第5名。

Multi-zone disaster relief AI env for Meta PyTorch OpenEnv Hackathon. 4-stage pipeline: PyTorch ZoneScorerNet -> Triage -> Planner -> Action Agent. False SOS detection, cascading failures, airlift precision.

Crucible Open Source (Basic): a minimal legal-agent orchestration framework (JP-law focused baseline), with mock-ready pipeline, prompt templates, and configurable adapters.

Cognitive architecture for emergent AI identity — blank slate to selfhood through lived experience

This project is designed to collect, analyze, and summarize news articles using AI. It integrates multiple news sources for collection and uses AI models such as DeepSeek and Gemini for analyzing the content. The system interacts with the AI to provide insights.

LLM Agent Builder

Website for "RecMind: Large Language Model Powered Agent For Recommendation" (NAACL'2024 Findings)

自托管 HTTP 编程 Agent 工作台：支持流式对话、持久会话、文件交付、后台任务和 Docker Chrome 真实浏览器访问。

SynapSense: Python In-Context Learning for Large Language Models SynapSense is a cutting-edge Python library designed to streamline the implementation of In-Context Learning (ICL) with Large Language Models (LLMs).

Scrapes newly posted jobs from a variety of sites and an ai agent filters them based off of the users resume.

A simple local python AI chatbot using HuggingFace inference API and streaming/history with Redis

mra is lightweight framework for building headless, programmable AI agents in Rust. Tokio-native runtime with built-in supervision, sessions, and tool use.

AstrBot 宿主上的多 Agent 编排内核：TaskAnalyzer → AgentCoordinator → SubAgent 三级调度 + MCP Bridge + Shipyard 沙盒；435 单元测试 / 99% 覆盖 / ruff+mypy+bandit 全绿

A tabular agent designed for question-answering on structured data from PDFs

A command-line interface for Ollama LLM models, designed for seamless integration with shell scripts and command-line workflows.

A demo app showcasing different architectural patterns commonly used when creating chat apps or agentic workflows with an LLM

RAG-Enabled Voice AI Agent for Calm, Clarity, and Everyday Emotional Guidance

Stop AI agents before they do damage — behavioral sequence detection blocks credential exfiltration, config harvesting, and secret leakage before the network call fires

DeterminAI is a deterministic, transactional AI execution engine that provides immutable, event-sourced workflows for AI systems.

This is a File system mcp server that could allow an LLM to read and list files from a specified safe directory on your local machine.

OneBot 11 协议 QQ Agent, 以 Golang 编写

Elicitation MCP server

🤖 Build and optimize an AI trading agent using JavaScript for efficient and intelligent trading decisions on financial markets.

SochDB is a high-performance embedded, ACID-compliant database purpose-built for AI agents - Examples