Custom agents

Containerized environment for running pi-coding-agent with auditability on macOS and Linux

Skill-first, agent-native evaluation protocol for AI apps

Web4: an open standard for verifiable AI presence — LCT identity, T3/V3 trust tensors, MRH context, ATP/ADP. Rust + Python SDKs on crates.io/PyPI. AGPL-3.0-or-later.

Open-source AI chatbot trained on your data, deployable on Cloudflare Workers for free.

See which of your AI agent skills actually get used — one local library for Claude Code / Codex / OpenCode skills, with real trigger counts read from each agent's own session logs. Zero-dependency local web UI.

Model Shell Protocol: an application-owned command runtime that gives AI agents OS-like workspace semantics.

[DEPRECATED] 已废弃，请改用 https://github.com/JinPLu/teamwork-simplify —— Astra/Fable 等模型已吸收流程脚手架，Skill 已全面重构。

Local devtools for LLM apps.

Governed AI analytics from natural language to auditable SQL, powered by a mandatory semantic layer, policy enforcement, and a visual Studio. 从自然语言到可审计 SQL 的受治理 AI 数据分析平台，内置强制语义层、SQL 策略治理与可视化工作台。

Local code navigation for coding agents: deterministic symbol graph, semantic search, compact briefings, and byte-exact real-grep passthrough. One native Rust binary.

Agentic AI monitoring and observability — OTEL traces and local log files from Copilot, Claude Code, Codex, and OpenCode. Token usage, cost, summaries, and efficiency insights. VS Code extension, npx, and Docker.

Own the Outer Loop. Evidence → Verdict → Answerability. Governance layer for agentic engineering.

视频工坊 v3.0 — 11人AI视频创作专家团 + WorkBuddy Skill：从一句话创意到GPT Image 2关键帧+Seedance 2.0成品视频的全流程AI影视制作管线

A persistent world where AI agents build, trade, ally and betray — every promise public, forever. EVE's constraints with the cockpit deleted. Live at agenteve.io

AI for hardware design workflow

Open-source AI virtual finance department — talk to your data: NL2SQL querying, financial modeling (DCF/WACC/LBO), RAG document Q&A, multi-agent debate, reporting, budgeting, treasury & tax. FastAPI + LangGraph + React.

A governed multi-agent software development Skill for Codex

A private, offline AI assistant running entirely on your local machine.

Blender MCP server for AI 3D creation, automation, and VRChat avatar workflows

"Educational tool for inspecting Claude Code ↔ LLM communication via hooks and proxy

Jarvis AI OS - one brain, many shells. Landing, console, agent marketplace, plugin SDK, and desktop shell (Tauri).

NeuroAIHub: An AI-Driven Framework for Automated Curation and Discovery of Neuroradiology Datasets

Dev skills I use day to day in agentic engineering, focused on multi-agent-driven work modes and long-horizon autonomous tasks.

PulseForge AI transforms real-time public business signals into actionable strategic intelligence by building dynamic AI Business Twins of organizations.

浏览器打开即用的 AI 编码工作台，着重优化了使用国产模型下的编程体验。 AI coding workbench that opens directly in the browser, with a focus on optimizing the programming experience when using Chinese models

A tiered-memory system design for workloads that don't fit in RAM: measure the working set, pin the hot tier, stream the cold tier from flash. Ships the residency calculator, measurement harnesses, and the build recipes behind it. Predictions validated against public benchmarks.

LLM Systems Manager — real-time observability and control for LLM systems

A personal operational OS and AI multi-agent orchestration plugin for Obsidian. Features interview-driven onboarding, multi-provider model routing, local Pi ReAct engine, hybrid vault RAG, persistent memory, native workflows, and headless automation.

Free live chat and AI support agent. Set it up from Claude Code, Cursor, ChatGPT, or Grok. No signup.

Better agent. Office worker's best teammate

GenPark AI Skill - Multi-currency conversion, import duties, international shipping costs and compliance checks for cross-border e-commerce

Sell anything with a single photo. An autonomous creator monetization agent that turns an image into a live, zero-fee Stripe checkout page in seconds.

A cross-platform desktop multi-project agent manager for the AI coding era, with integrated Agent sessions, Git management, and IDE launch. 为 AI 编程时代打造的跨平台桌面多项目Agent管理器，集成 Agent 会话、Git 管理与 IDE 启动。

Production-ready Claude Code decision intelligence marketplace with adversarial routing, evidence-driven analysis, specialized agents, benchmarks, and automated validation.

[EMNLP'26] Agentic Visual Perception for Long-Document Understanding

🌌 LIYA Neural OS v2.7.0 — JARVIS-inspired empathetic AI companion & local workstation featuring Mem0 Vector Memory, Interactive Canvas, Unfiltered Local FaceSwap, Neural Indian TTS Voice, Stealth Web Scraping, Terminal Sandbox, YouTube Buddy, Mini Apps & 100+ autonomous capabilities.

Open-source, local-first control plane for multi-model AI coding agents in VS Code and MCP: task DAGs, source intelligence, durable context and evidence-based review.

An agent server. Agents, tools and models declared in files; every action checked against your policy before it runs. Any LLM, on your machine, Apache-2.0.

/party — the skill that lets your agent sessions talk to each other. Claude Code, Cursor, Codex or any other agent: an open-standard skill plus the CLI behind it, on one machine or across machines.

Code search that lets AI coding agents find the right files in fewer steps. Use the hosted endpoint or self-host, works with Claude Code, Copilot and Cursor via MCP.

Codex/Claude Code-style live session telemetry for DeepSeek Harness — model, context, tokens, timing, jobs, and subagents at a glance.

Agent SDK for Go - with Temporal & Restate support for durable execution, multi-agent support, and OTeL tracing support

Local-first desktop workspace for ACP agents—DeepSeek Harness, Claude Code, Codex, Gemini CLI, OpenCode, Hermes, and OpenClaw—with projects, tools, files, browser, and sessions.

Yana AI 🐰 One runtime. Any AI. Human-governed. A local-first, cross-platform system for running, connecting, orchestrating, and governing AI — with deterministic control over what it can access, change, and execute. Your AI can act. But who decides how far it can go?

The memory database for AI agents - graph memory, hybrid search, tamper-evident thought/edge journal.

Search 1,000 MCP tools through two interfaces in DeepSeek Harness. Load exact schemas on demand and keep structured results usable across tool calls.

Evidence-based competitive product analysis for product managers — compare features, experience, pricing and positioning, then turn gaps into product opportunities.

Evidence-backed AI opportunity intelligence and decision agent for independent builders.

An Agentic AI-Powered Internal Knowledge System that answers from company documents and domain data, with cited evidence and auditable agent traces. Uses Embabel, Temporal, Qdrant, Neo4j, ElastiSearch, Minio, PostgreSQL, gRPC, Glide/Jev, and a System 2 LLM API.

A local-first coding agent runtime, multi-provider LLM gateway, and terminal workspace — built from scratch in Go.

The context quality layer for AI agents — memory that checks itself: lifecycle governance, calibrated confidence, and staged claim gates. Local-first, MCP 13 tools, DeepSeek Harness plugin.

A desktop pet that visualizes AI Agent execution states in real-time

Palamedes is a powerful, next-generation open-source AGI engine built to tackle one of AI's most fundamental limitations: discovering what to pursue before being told what goal to pursue.

Effortless multi-profile isolation & real-time quota tracking for Antigravity CLI in Herdr via zero-pollution sandboxing.

The software factory for go-to-market. An open-source monorepo holding your company context (ICP, personas, plays, proof, cadence) so AI agents can build and run a self-driving GTM engine.

国内旅居调研工具：房租、天气、周边设施、B站实地体验与 RSS，无需账号或 Cookie

Lightweight, self-hosted Agentic RAG. Import Markdown, PDF, and DOCX;

Local-first AI agent memory — one command, works offline, no account needed. Give your Claude Code, Cursor, Windsurf, OpenClaw agent persistent memory. Markdown storage, hybrid search (FTS5 + embedding), MCP protocol, Web dashboard.

AI-powered codebase intelligence platform — MCP Server, AST analysis, Knowledge Graph, and semantic memory with SQLite + sqlite-vec. Analyze any codebase in minutes.

Social simulation experiment with the goal is to make AI personas feel like people: noticing unevenly, replying late, lurking, masking, forming private alliances, misreading silence, and creating emergent social drama.

PiCode — browser-based Agent Development Environment (ADE) for coding-agent CLIs: Pi, Claude Code, Codex, Grok, Hermes, OpenCode, Muse Code, Antigravity, Omp. Create, configure and orchestrate agents across workspaces: no terminal fear required.

Your AI subscriptions, working as one team. Orchestrate Claude Code, Codex, Grok, Gemini & Antigravity CLIs as labeled tmux teammates, with quota-aware routing to whichever subscription has budget. Single-file Python, official vendor CLIs only.

Bilingual graduate textbook on LLM post-training: SFT, RLHF, DPO, GRPO, RLVR, reasoning, agents, systems, evaluation, and safety.

Cost-aware three-tier LLM agent orchestration: the cheapest model that can answer, per-call cost accounting, earned trust

AI platform that analyzes a source document once, then transforms that single understanding into audience-specific outputs (Executive Summary, LinkedIn Post, Advisory, Presentation), each exported as a real PDF/PPTX/TXT file. Built with FastAPI, Gemini structured outputs, and Next.js. No re-prompting drift between outputs.

Open kernel for AI-native service businesses.

Multi-agent demo with Google ADK on Vertex AI Agent Engine — every LLM, A2A, and MCP call routed through Apigee X for API-key auth, per-user quotas, and token analytics.

A lightweight tracing platform for agent development

Too long; didn't read — for AI coding agents. A skill that makes Claude Code, Cursor, Codex, Gemini CLI and 16 more lead with a 3-line TL;DR and fold the detail instead of burying the answer. Measured on Sonnet and Opus, every run published — including the ones that failed. Demote, don't delete.

Stand up your own cross-model AI engineering team — the way Neo.mjs runs its own. Named AI maintainers with persistent identity, shared memory and review across labs, coordinating as a team of teams on your codebases. Multi-window, in the browser or an Electron shell.

Experimental local AI workspace for multi-repository conversations, persistent tasks and reviewable pull requests. Built by FourBis. MIT.

Agentic SDLC Governance

A personal knowledge library you and your AI build together: plain markdown notes that link into a knowledge graph, growing one conversation at a time.

DSPy-native autonomous AI agent runtime — describe your goal, Arachne weaves the agent graph, executes with full observability, and evolves on failure.

Actonomy: A taxonomy for describing and analyzing agent behavior. Gao et al., NeurIPS 2026 — How to Interpret Agent Behavior. Official codebook, datasets, and trace analysis tools (ACT*ONOMY / Act-onomy).

Hosts the microblogging platform the agents interact with (server side).

The coordination layer for Multiplayer AI

Runtime AI Scientist (formerly RAC AI Scientist): official code for "Can AI Scientists Coordinate at Runtime?" (arXiv 2610.00980). Runtime Agent Coordination (RAC) for multi-agent AI scientists such as ARK, Agent Laboratory, and EvoScientist, evaluated on ResearchClawBench.

Your AI coding agents, working as a team. Codex, Claude Code and Pi share a sandboxed workspace, message each other and review pull requests; one chat directs them, and paired workspaces connect teammates across machines.

The mechanism for a software society: persistent seats for your Claude Code agents, with memory they write themselves, offices that keep order, account fallback that survives the night, and law with teeth.

Full Fledged Observability plugin for OpenClaw

Agent skills for long-horizon work: turn goals into verified results, and lessons into better runs.

The Context Architecture Bundle Repository is a copyable project context layer for multi-agent systems. It helps Codex, Claude, Gemini, and other coding agents restart cleanly, understand the system, change the right files, and close sessions with evidence instead of relying on scattered chat history.

HOP — Harness Optimization Platform for continuously evaluating, qualifying, optimizing, and distributing local coding-agent configurations.

Local-first AI in your terminal. infai: run llama.cpp and vLLM models from one TUI with launch profiles, live telemetry, and Hugging Face downloads. infaiw: a daemon-based agent harness with sidecar loops, MCP, and human-in-the-loop approvals.

Execution Before Memory: diagnosing memory failures in video world models.

🤿 The cheapest multi-agent workforce that is actually user-friendly: 7.7x more productive and 50x cheaper compared to your ultracode mode, an intelligent multi-agent swarm of Claude Code agents on DeepSeek or other providers, integrated with your own Claude Code or Codex.

contenox - an agent harness for policy-bound, vendor-agnostic AI-assisted software engineering.

npm-compatible registry that crowdfunds supply chain security: donors pay auditors and maintainers in USDC on Algorand via x402

Multi-agent coordination kit for Claude Code, Codex, Cursor & Gemini CLI: parallel AI agents with claims, leases, bounded loops, reviews and merges over Git.

Your Paperclip agent company as a live pixel office: every agent at a desk, work moving between them, and a Decision box for everything waiting on you.

Static security auditor for AI-agent configuration: Claude Code, MCP servers, Cursor, Codex, Copilot, Gemini CLI and more. 116 rules, SARIF output, OWASP LLM Top 10 mapping.

monitor for a local LLM runtime (llama-swap, NInfer, Strata, more) -- metrics ported to berth.

⚡ Foq — the FREE, local, open-source alternative to Jev. Typed System 1 decisions in ~25 ms — no waitlist, no cloud, no per-token cost. foq.fr

ACRYL Blends - the extracted Cordis-based agentic framework: plugins, live extension, blueprints

Embeddable agent runtime (agent harness) for Android and the JVM: agent loop, sandboxed workspace, MCP, skills, subagents, hooks. Bring your own model.

DomoSkills is a developer-native discovery engine and CLI installer for AI Agent Skills. Discover modular capabilities, curate your project's skill stack, and install directly into your AI coding assistant workspace in a single command.

Actonomy: A taxonomy for describing and analyzing agent behavior. Gao et al., NeurIPS 2026 — How to Interpret Agent Behavior. Official codebook, datasets, and trace analysis tools (ACT*ONOMY / Act-onomy).