Custom agents

Autonomous A-share quantitative trading strategy optimization powered by AI agents

基于生命周期钩子的轻量级 AI Agent 框架 — 插件即文件，全异步，零 SDK 依赖

RADAR: Redundancy-Aware Diffusion for Multi-Agent Communication Structure Generation (ICML 2026)

Iterative optimization for AI agents. Turn models into accurate, structured, production-ready systems.

A cognitive substrate for AI agents — hyperdimensional memory with first-class goals, beliefs, sensory, self-model, and a non-destructive unlearn primitive. Rust top to bottom, embedded-first, no LLM in the read path. One binary, no query language.

Local filesystem MCP server with 50 tools: safe delete, process management, interactive sessions, async search, OCR, ZIP, Markdown/PDF export, and cloud-lock-safe operations.

DesireCore Agent OS. An open, delegation-based AgentOS (Agent Operating System) — a teachable, file-based AI companion desktop app you can grow.

Multi-agent harness for AI coding tools. Crash-safe state, parallel execution, one CLI.

Unison (万物一心) — A local-first, file-driven Loop Engineering pipeline where AI agents plan, build, challenge, and verify work until PASS. | 本地优先、文件驱动的多 Agent 循环工程管道。

Human-gated perspective-panel research: one question, several seats, one judge. Solo, native panel, or per-seat MoA/Fusion fanout.

A human–AI collaboration framework that works with LLM nature, not around it — natural language and purpose make RAG and agent orchestration unnecessary. Home of the Pang Principle.

AI-powered interactive animated story generator — script, SVG art, and animations generated by Claude agents on AWS

情感引擎 × LLM 的数字人 — 贝叶斯主动推断确定性地生成情绪，LLM 只在输入/输出两端结合；三时间尺度+稳态、短时注意力与长时记忆的桥、可指定人格

The agentic runtime to build production-grade AI agents at scale.

Echo-CoPilot: A Multiple-Perspective Agentic Framework for Reliable Echocardiography Interpretation

Manage containers on docker, podman, compose, and docker swarm through an MCP Server for Agentic AI

ServiceNow Coding Standards for Humans and AI Agents.

Local-Ai Agent with custom integrated tools & skills. Ultra-light. Hyprland, Omarchy, Odysseus, and Hermes.

A curated survey of embodied agents:robotic memory, planning, world models, verification, and failure recovery

A local, provider-neutral runtime for governed software agent loops.

redteam is a multi-model harness that forces an independent reviewer to challenge AI-generated code before it ships. Apache-2.0.

Clean-room, Rust-first, Asupersync-native Snowflake SQL API connector for coding agents: deterministic JSON envelopes, capability registry, MCP server, TUI. 14 crates on crates.io; live reads proven at the driver level, writes implemented but end-to-end live run still pending. No ODBC, JDBC, or Tokio.

Open-source DeepWiki alternative: AI-generated documentation and natural language Q&A for any Git repository.

VibeCoded Tools - Orchestrator: improve your Claude Code!

Single-process database for AI apps: vector, graph, lexical, and hybrid search with durable jobs in one binary.

Keep only the relevant context. AI as a tool.

Shellless and rust only llm agent

Reference template for building production-grade MCP servers for Bitrix24. Nuxt 4 + @bitrix24/b24jssdk, tested, deployable, with an agent feedback loop built in.

Bodhi — a local-first AI agent workbench in Rust: desktop app, Bamboo runtime, Jiandu shared memory, Nova computer use and Magpie IM bridge.

A collection of AI agent skills focused on medical imaging and healthcare workflows. Built for radiologists, healthcare IT professionals, and researchers who want AI coding agents to help with imaging workflows, clinical documentation, AI integration, and medical research. Works with Claude Code, Codex, Cursor, Windsurf, and many other agents.

Curated, annotated list of multi-agent systems resources — MARL, game theory, negotiation, LLM agent teams, MCP/A2A protocols, benchmarks, and frameworks

Awesome paper list for LLMs in politics, geopolitics, policymaking, strategic studies, and decision-making

Fan out heavy-lifting tasks from Claude Code (or other AI coding agents) to parallel Gemini sessions via the Antigravity CLI, then integrate the results.

面向 LLM Agent 的 CTF 知识图谱 — 基于 Karpathy/LLM Wiki 三层架构

AGENTS.md, command contracts, skills, and verification rules so agents stop guessing.

Make your Claude Code agent work like a real harness (Hermes). Self-evolving skills + drift prevention. Research-backed.

Turn coding agents into work owners. A vendor-neutral backbone that takes a GitHub issue to a merged PR: readiness check, isolated worktree, multi-agent review, CI and evidence gates, merge window. Claude Code, Codex, Cursor, Antigravity.

Vimeflow is a coding agent TUI view park(manager) built with libghostty in MacOS and Xterm in Linux

Worktree-centric libghostty-based terminal multiplexer for macOS, iOS & iPadOS

Routed Media OS 2026: 96 AI Skills, 13 Modes & 7 Agents for FFmpeg, OBS, DeckLink & Dolby Vision

Autonomous AI product factory — one sentence in, full SaaS out. Five agents: Architect, Scaffold, Coder, Security, Deploy. Runs on Ollama (free) + Claude fallback.

Multi-Agent AI legal assistant for solo lawyers practicing Chinese law. Model-agnostic, plug-and-play. 为执业中国法律的独立律师打造的多 Agent AI 助手 — 模型无关、即插即用。

A framework-neutral taxonomy of agentic-AI artifacts, organized around what matters in production: versioning, inspectability, and governability.

Self-hosted runtime authority server for AI agents — budgets, risk, actions, tenant isolation

Proof-oriented registry of reusable AI-agent operating loops

An Agentic Framework that forces System 2 thinking from LLMs and reduces Token Burn.

Enterprise AI platform built on the Universal Knowledge Graph (UKG), featuring a 17-Axis Knowledge Framework, 10-Layer Truth Engine, multi-agent orchestration, GraphRAG, MCP integration, explainable reasoning, governance, compliance, and end-to-end audit traceability.

基于 RAG 的《明日方舟》剧情问答 AI 助手，支持多模型接入与一键更新知识库

Self-hosted, privacy-first AI home companion with voice, touch and long-term memory.

AI-first workflow and loop engineering practice

Structured planning, bounded memory, TDD, and Git guardrails for local coding models in Pi Code (I don't know TypeScript at all; this is mostly a local-model experiment, with occasional help from Claude Code)

Infinite canvas for brainstorming with AI

MCP server for marketplace search & price data — TCGPlayer, Reverb, Thumbtack, OfferUp, Craigslist + contractor/nurse license verification + PSA grading

Self-hosted AI customer support. AI agents that resolve requests, not just answer them: order lookups, refunds and order updates via Shopify, WooCommerce and Stripe, with human handoff. Web chat, WhatsApp, Instagram DMs and email.

A hybrid AI assistant framework linking structural workflow engines and reasoning LLM agents through LangGraph-powered session control and task switching. 混合 AI 助手框架，通过 LangGraph 驱动的会话控制与任务切换，连接结构化工作流引擎与推理型大模型智能体。

Autohand Routes - the model router built for coding agents: policy-driven, provider-agnostic, and battle-tested aross millions of sessions.

Turn a book or document into a modular Agent Skill pack: atomic skills, combo workflows, a router, references, and validation.

BYO-LLM multi-agent harness: hybrid DAG orchestration, router, two-tier memory, streaming-primary event model, sandboxed tool execution (native + Docker)

Open-source local-first AI assistant runtime with graph memory, semantic tool routing, markdown-governed tools, FastAPI/Next.js frontend surfaces, and verified tool calling.

A Claude Code template for running a content/design business as a solo operator. One orchestrator + several worker sandboxes; briefs as handoff contracts; ICM-aligned context layers (L0/L1/L3/L4); weekly + monthly maintenance routines; four hooks, two skills, one canonical example brief.

One desktop window for ChatGPT, Claude, Gemini, Grok, Perplexity, Qwen, DeepSeek and Z.ai. Fast, private, fully local. Built with Tauri and Rust.

AI pair-programming IDE for macOS — native SwiftUI app with a project-aware Claude Agent SDK runtime.

Intent in, outcome out. A self-healing, self-learning/hill climbing harness that drives coding agents to a proven outcome instead of a claimed one.

MCP server for PostEverywhere: let Claude Code, Claude Desktop, ChatGPT, Cursor and other MCP clients schedule posts to 13 platforms: Instagram, X, TikTok, LinkedIn, YouTube, Facebook, Threads, Pinterest, Bluesky, Telegram, Discord, WordPress and Google Business Profile

CodeGraph — code-intelligence engine for AI agents. One 5MB Rust binary indexes any repo into a resolved, zero-phantom-edge knowledge graph (MCP + CLI): callers/impact/flows/risk-review, cross-service route hubs, serverless semantic search, Swift compiler-grade via Xcode IndexStore. ~20-100x fewer agent tokens than grep.

A cross-tool handoff skill for Claude Code and Codex CLI: generates context handoff docs, updates STATUS.md, snapshots commits, and prints next-session prompts.

AI coding agent runtime that makes LLMs understand your codebase with repository-aware context, memory, and continuous learning

A curated list of OpenClaw resources, tools, skills, tutorials & articles. OpenClaw (formerly Moltbot / Clawdbot) — open-source self-hosted AI agent for WhatsApp, Telegram, Discord & 50+ integrations.

Durable task planning for Codex/AI coding agents: recovery, bug memory, Mermaid-first design, verification evidence, and safe multi-agent collaboration. 为 GPT-5.6 深度优化，也兼容其他模型。

Provider-neutral multimodal OCR CLI and MCP server(+ web app) for images, PDFs, URLs, structured extraction, and agentic workflows—Gemini, Kimi, Muse, OpenRouter, and Cloudflare AI Gateway.

面向 MetaTrader 5 (MT5) 的 AI 交易助手与 EA 工程化框架。AI trading assistant and EA engineering framework for MT5, built with Python, MQL5, MCP tools, LLM agents, and risk modules.

AI-first self-hosted home cinema deployment and media ingestion pipeline

A quantum prompt playground & macOS-native Rust coding agent: morphing fluid entropy into rigid execution checkpoints. Entropy cannot lie.

JetBrains/PyCharm plugin to review an agent's changes in your IDE and relay batched, line-anchored comments back into its running session — instead of retyping feedback into the terminal.

A self-improving intent engine for autonomous work.

Complete guide to run Claude Code CLI & VS Code with AgentRouter using a WAF bypass proxy

AI Engineer MVP: A deployed multi-agent AI system with parent–child orchestration, energy-based routing, and LLM-powered task, research, and email agents.

Multi-agent AI orchestration framework for Python

Wolbarg — modular, provider-agnostic semantic memory SDK for AI agents

Dial your agent into your next meeting - powered by the Looped Agent Framework

An Operations & Automation Specialist AI Agent powered by OpenClaw — bridging high-level strategy and reliable, scalable execution through intelligent workflow automation and process orchestration.

Agentic AI for Cold-Chain Sustainability: LSTM-Based Predictive Logistics

Failure Compiler for AI agents: turn failed outputs into replayable regression cases.

🕹️ Gamified Vibe Coding, with full controller support, mini-games, themes, and more!

Reusable agent skills for battle-tested engineering judgment. Works with Claude Code, Cursor, and 10+ AI tools...

AI-powered research reasoning agent for research gap discovery, novelty assessment, and implementation guidance.

Content Distinctiveness & Information-Gain Auditor Powered by Brewcontent AI

Your personal Claude assistant, running on OnCell — a NanoClaw fork where every agent lives in a durable cloud cell instead of a container on your laptop. Isolated, crash-proof, remembers everything, costs ~$0 while idle, wakes on your next message.

Self-hosted AI agent you talk to on Telegram. Docker, full tool access, 850+ skills, voice in and out, layered security.

Deterministic AI agent orchestration — comment via Discussions & Issues; code changes by maintainers only.

A Query-Local Unified Risk Modeling Framework for Corpus Poisoning Attacks

An end-to-end AI-powered mobile productivity assistant that transforms natural language into reliable actions for managing tasks, meetings, notes, and progress. Built with intelligent language understanding, deterministic execution, and workflow automation for efficient productivity management.

RAG-ChatBot for Vietnamese Legal Document

A safety preflight tool for Claude Code and Codex that decides whether a coding task should loop, then generates a bounded execution contract.

StudyStudio 是一款融合了前沿 AI 技术的全方位学习管理系统。它致力于将知识组织、任务规划、笔记记录与智能练习有机结合，为每一位追求效率的学习者提供一站式的“数字化第二大脑”。

Pulse — Hermes-style self-improving AI agent. Reliability-first rebuild with evaluated skill self-evolution, multi-agent team orchestration, dialectic user modeling, and fully self-hosted default stack (Ollama + SQLite FTS5). Apache 2.0 license.

git blame tells you who. gitwhy tells you why — provenance for AI-written code (Claude Code + Codex), 100% local.

A shared knowledge vault + full software-engineering workflow for AI coding agents — run Claude Code and Codex in parallel with one memory, one plan.

Connects the AI agents you use: your agent hands a task to another and gets the answer back

Cognitive OS v3.0 — Universal AI agent operating system specification. 16-section cognitive architecture for Claude Code, Cursor, Codex, Gemini, and Factory Droid. Multi-harness prompt engineering with verification chain, swarm coordination, and adversarial security.