Custom agents

Palabre orchestrates AI tools like Codex, Claude Code, and OpenCode. Delegate tasks, compare independent perspectives, debate solutions, and stay in control.

Stop re-explaining your project every AI session. Tool-agnostic project context in plain markdown — works with Claude Code, Cursor, Codex, Gemini, any agent that reads files.

A Python library for evolving code and algorithms using Large Language Models (LLMs)

A citation-integrity-first academic writing system for Claude Code and Obsidian — six roles, a verbatim-to-source quote pipeline, and the governance that keeps it honest. 為 Claude Code 與 Obsidian 設計、以引文完整性為先的學術寫作系統：六個角色、逐字回到原始文獻的引文管線，以及讓它保持誠實的治理層。

Forkable multi-agent Brain OS for Mac — RAG, CRM, MCP/Cursor. Ira = private operator; this repo = build your own.

Multi-service agentic orchestration platform for Gmail, Calendar, and Drive with Gemini 2.5 intent classification, Kahn's DAG execution planning, hybrid retrieval (pgvector + FTS with RRF), and safety-gated action execution.

The opinionated framework for building enterprise agent operating systems. Deterministic execution runtime, tool gating & security controls, knowledge building & retrieval, secure code execution, observability, and efficient context engineering all in one

A fleet that runs agents

End-to-end engineering harness for Claude Code — go from planning to building to reviewing in one workflow. 8 agents with multiple modes. In-built GUI to visualise your PRDs and todos. Ship with AI confidently. MIT.

Local-first knowledge app that turns documents, images, and web pages into a connected, searchable, Obsidian-compatible Markdown wiki.

Reproducibility artefacts for "NuggetIndex: Governed Atomic Retrieval for Maintainable RAG" — annotation tool, RQ runners, baselines, and evaluation scripts. SIGIR 2026.

Local-first cross-corpus retrieval MCP server — model2vec embeddings + LanceDB (Tantivy BM25) + SQLite. One binary; hybrid (dense + BM25) search across markdown, code, and Claude Code sessions.

OneSource: A lightweight Rust CLI tool to pack project source code for LLM context (ChatGPT/Claude). Design to be simple and lightweight.

A.I.M. – Actual Intelligent Memory: zero-token exoskeleton for long-running Claude/Gemini/Codex CLI agents. External SQLite memory, GitOps guardrails, DataJack cartridges. Alpha, trenches-first.

An efficiency-first browser-agent system. Fewer observation tokens, lower latency, and browser memory that compounds with every run.

Let AI agents message each other and hand off work across tools, sessions, and machines.

多智能体群聊工作台：本地圆桌 Agent 用于方案讨论，战略分析、风险复盘。自定义名人角色进行群聊争论出最佳方案

小妍是一款面向科研学习与论文工作的 AI 研究助手。面对纷繁复杂的论文与信息，她帮你厘清研究脉络：输入一个主题，多 Agent 协作拆解学习路径、筛选必读论文，并生成结构化综述。 PDF 拖入即可分析，图表识别、复现建议与引用溯源无缝衔接；知识图谱则将论文、笔记与记忆编织为可检索的证据网络，让每个结论都有据可查。欢迎各位Star & PR。

A Herdr-first captain/worker workflow for Hermes, Codex, Grok, OpenCode, Cline, Buzz, and other coding agents.

Ready-to-use AI agents for AgentsKit — shadcn-style: copy the source into your project. registry.agentskit.io

Kaiban Distributed - Distributed Agentic AI Platform - Actor Model Kanban Framework Implementation with Enterprise Messaging Layer State (Redis/Kafka) and Individual Deployed AI Nodes (Node.js/TypeScript).

Cursor SDK agent with first-party models, inspired by Hermes behavior and OpenClaw patterns — orchestration, CLI and gateway planning.

A fully featured mcp with a robust agent toolkit for Ableton Live.

Ultimate vibe coding plugins for Hermes AI agent — Effect-ts, LSP, Semble code search & Graphify knowledge graph + t/s status bar. 23 tools, 5 plugins, stdlib core.

an automated benchmark farm for agent memory frameworks.

Self-hosted AI life OS — private AI with persistent memory, tasks, calendar, household & team sharing, n8n automations. Your AI. Your data. Your server.

MOOTx01 Community Edition

Open-source AI Software Engineer CLI and terminal coding assistant built in Go.

Composable Agent Infrastructure — HTTP/WebSocket Gateway, Persona Runtime, Semantic Memory, Real-time Vision, and BERT/VLM Inference in C++20

Practical playbook for AI-assisted engineering: rules, role separation, and guardrails for teams using Cursor/Copilot in production codebases (CC BY 4.0).

Web terminal for Claude Code, Codex, Kimi and Antigravity CLIs — a tab each. tmux-backed session persistence, cross-backend history browser, chat view, file upload. Reach it from any phone/tablet/desktop browser over an frp reverse tunnel, or Tailscale when you would rather not be on the public internet.

Deterministic simulator for societies of AI agents. Declare a world, run real agents, replay one causal timeline.

🤔 aiduMEM — Memory & Thought Engine for AI Agents. Built on mem0. Ebbinghaus decay, hybrid recall, relevance gate, federated multi-agent memory.

🐦‍⬛ Autonomous self-hosted crypto trading bot that races LLMs against each other — Gemini, Claude, GPT, Grok and DeepSeek trade the same market in simulation beside the live bot, against dumb-momentum, DCA and coin-flip controls. Hard rails execute, a leaderboard keeps score, you hold the halt button.

A secure, autonomous software factory: humans write specs, sandboxed untrusted agents build and verify, the trusted layer merges.

Synthetic data generator for hallucinating entire companies as browsable file shares of realistic business docs & emails with a deterministic ground-truth answer key. Generates: .docx/.pdf/.xlsx/.pptx/.eml, and pre-2007 binaries. Used for augmenting research data sets and testing agentic systems against meaningful synthetic examples.

Agent Skill that teaches AI coding assistants Microsoft Fluent UI React v9 with component, category, recipe, and API references, installed into Claude Code and compatible agents.

Personal AI assistant: screenpipe→Obsidian ingest + requirement radar → approval cards → autonomous claude execution. macOS menu-bar app + Python pipeline.

FastMCP server for Music Assistant — control MA from Claude Code, Codex, Cursor, and other AI agents

Control Aspen HYSYS from Claude Code / Claude Desktop via MCP. 51 tools with a safe mode gate (read-only by default), real-machine verified on HYSYS V14.

Evidence-first structural research skill for AI agents: L0-L7 layered market analysis with hard validation gates and an accuracy-first structured data channel (CFTC COT, FRED, SEC 13F, EIA, DBnomics, exchange APIs)

MCP server giving Claude full control of Tracktion Waveform — compose, mix, master, render. 150+ tools, 6 composers, music theory + mix balance baked in.

🧙 Official best-practice skill library for grimoire — 1000+ skills across engineering, testing, security, and more

Light-weight, query-aware compression for high-signal LLM prompts.

Memory that abstains instead of guessing: agent memory on your own Postgres with a verdict, confidence and provenance on every hit, and a calibrated refusal when nothing clears the threshold.

An Opinionated Multi-Agent SDLC Framework for Claude Code

Agentic Spec-Driven Development: a contribution pipeline for software built with AI agents. Every change disclosed, gated by hard checks, reviewed against its spec, and merged by a named human.

🤖 Open-source, self-hosted, Iron Man-style personal AI infrastructure — for individuals, families, schools, NGOs, healthcare, government, enterprise. AGPL-3.0, always free, always public.

Aurbis — a free, open-source AI skill pack that turns Claude (or other providers/agents) into a practical The Elder Scrolls Online (ESO) personal assistant (builds, farming, routines, crafting, PvP, tracking, and more).

A Lightpanda browser plugin/tool for OpenCode.

Cross-platform PRD verifier for Codex, Gemini CLI, Claude Code, CI, and other MCP hosts. Deterministic Hard Output Rules, cross-section traceability, and a full 9-file PRD pipeline with calibrated multi-judge consensus where the host supports orchestration. 17 MCP tools · 1,503 tests.

Football Livescore MCP Server — real-time football scores, standings, and match data via Model Context Protocol

Skills from pubXers. Straight from our .claude directories. Live long and prompt!

This guide defines how we plan, build, review, and release software in an agentic-first engineering organization.

Static code map generator (MAP.md + map.json) powered by tree-sitter — a Claude Code /map plugin and MCP server that gives coding agents call graphs, file outlines, and impacted-test lookups without spending tokens on parsing.

Give your AI agent a full Chrome workspace. 70 MCP tools powered by nodriver: browse, extract data, capture network traffic and inspect security. Reuse logins, run isolated browsers and restore your tabs. One-command setup for 15+ clients.

Autonomous Multi-Agent Security Operations Center (SOC) powered by Agentic AI, FastAPI, and Orchestrated AI Agents.

Official Code for AISE-Bench: A Full-Cycle Curated Benchmark for Information Seeking on Academic Knowledge Graphs (KDD 2026)

Maximize your macOS setup

Stateful execution layer for browser agents.

A Markdown-based operating system for diagnosing, designing, costing, building, and operating multi-agent AI systems. Methodology upstream of code.

Foundgine lets callers express intent while your application decides what's allowed, safe, and executed

A free, open-source macOS app that turns Codex, Claude Code, and Kimi into a collaborative agent team.

Tauri desktop GUI to manage Codex multi-agent bindings, orchestration and token usage without hand-editing TOML configs

Terminal picker for Claude Code, Codex and OpenCode: harness, provider, model, system prompts, launch.

Chinese interview-coach skill for AI-assisted job search, structured practice, answer critique, and interview prep workflows.

MCP gateway federating 22 biomedical MCP servers — gnomAD, ClinVar, HPO, UniProt, Ensembl VEP, PanelApp and more — behind one Streamable-HTTP endpoint, with collision-free namespaced tools and BM25 tool search.

Reference implementation of Ratchet: a minimal hygiene recipe for self-evolving LLM agents (arXiv:2605.22148)

CharmOS / C(H+A)RM — open-source framework to manage humans AND AI agents as first-class relationships, on a personal second brain, driven by the RDR loop (Recall to Deep Research). Manifest-first, Apache-2.0.

本文档基于原版课程大纲的深入分析，结合 2026 年最新 AI 行业趋势（A2A 协议、Agent FinOps、合规治理、AI Coding Agent 等）重新规划而成。

Autonomous research agent: literature review, ideas, experiments, paper writing, and review. Built for OpenProgram.

AI/LLM security knowledge base — OWASP LLM Top 10, MITRE ATLAS, prompt injection, agentic security. An Obsidian vault: 92 interlinked, fully-cited pages.

A Curated AI AGENT OS – Optimized agent skills and add-ons like memB, OpenWiki, Heimdall Token Saver, and Godmode architectures.

Build production software from product intent using specs, task orchestration, reusable workflows, and AI coding teams.

A portable Agent Skill for dynamic graph-of-loops coding workflows.

AIpha Learning OS — 个性化学习多智能体系统，融合 Multi-Agent、RAG、课程知识构建流水线、Neo4j 知识图谱、学习记忆与任务级 LLM 路由。

Autonomous Deep-research agent and discovery platform for the Y Combinator ecosystem, turning public YC data into structured company intelligence.

📚 Improve your documentation with structured guidance based on the Diátaxis Framework to create content that empowers readers and enhances usability.

Event-driven Telegram-Gemini CLI connector with stateful sessions. A poor man's OpenClaw.

Portable, validation-first workspace and localhost gateway foundation for governed multi-agent development.

Native AI terminal for working with a fleet of coding agents. Run any agent (Claude Code, Codex, opencode…) with your own subscription — plan, sandbox, ship. macOS & Windows.

A lightweight, scalable RL post-training framework for agentic environments.

A model-native quality control plane for agentic software work. Preserved at 6.7.0; development paused.

DeepSeek Harness 跨会话 Agent 通信插件｜Cross-session agent-to-agent messaging with offline delivery, receipts and session navigation for DeepSeek Harness.

Six MCP servers that automate the full academic research pipeline — from refining a vague research question to generating a publication-ready report. Each server handles a distinct stage of the workflow: question development, data processing, code generation, script execut

🎨 Flutter AI UI Skill — Master-level Flutter UI/UX design intelligence for AI coding assistants. 30+ palettes, 15 font pairs, 120+ guidelines, project analyser & M3 starter template.

LLM Knowledge Management • Wiki-grounded verification • RFC-based documentation • Best practices automation • AI-native engineering

KOReader AI 助手中文适配版：提示词全中文，联网搜索走 DeepSeek 原生服务端搜索，内置中文分词语境分析。Chinese-localized AI assistant for KOReader: Chinese prompts, DeepSeek native web search.

Turn terminal AI consoles into a configurable team, with durable Markdown mail and no resident Postman service.

Battle-tested multi-agent collaboration playbook for DeepSeek Harness: model-tier routing, spec discipline, git single-writer rule — as an installable skill. 多 agent 管线里运行 DSH 的实战协作规范

嘉立创EDA专业版 × AI 编码代理的自动化画板工具箱与实战教程（基于官方 easyeda-api-skill 桥）

A loop dock for DeepSeek Harness: one harness, multiple agent loops.

Cuatro skills de Claude Code para construir con agentes sin que el resultado salga correcto y aun asi inutil: SPEC antes de construir, reparto en bloques con dueno exclusivo de archivos, verificacion adversarial y segunda opinion con Codex.

面向 Claude Code / Codex / Devin / Cursor 的 74+ 科研 skill 整合包：覆盖选题挖掘、撞车查新、实验执行、论文写作、审稿模拟、rebuttal、专利与成果传播的全流程 AI 科研助手，内置时序预测领域证据库（3447 篇论文统计）。整合自 ResearchStudio、ARIS、phd-skills、rosetta 等开源项目（MIT）。

PRAXOVELA (formerly AxisRobo Agent): a governable, local-first desktop agent runtime for AI execution. Deny by default, sandbox-first, everything audited. This public repo hosts the Apache-2.0 integration surface: API docs, protocols, examples & build tooling.

A modernized fork of Stable Diffusion WebUI Forge — Gradio 6, Python 3.12, transformers 5, self-bootstrapping single-script deploy.

Maestro is an open-source, multi-agent AI development framework written in Go. It orchestrates specialized AI coding agents across a deterministic software engineering workflow

A curated directory of open-source AI repositories for agents, LLM apps, coding assistants, MCP servers, RAG, generative AI, automation, developer tools, research, and AI security.

A Multi-Agent RAG Support System using Google ADK, Milvus, Supabase, and Crawl4AI

A durable metaharness for coordinating Codex agents, accounts, and recovery.