Custom agents

Open-source multi-agent AI engine written in Rust. Turns any intent into coordinated research, analysis, and synthesis.

Step-by-step implementations for building cognitive financial agents

Prompt Distance (PD): a whitepaper-grade metric for how many prompts away a project is from not existing

Open source, automated memory layer that builds as you work.

Product-deep-dive is a skill for creating long-form AI product teardown documents in Feishu/Lark Docs. Help AIPM make a deep-dive of AI product.

Ronin is native Linux intelligence app with threaded AI chat, context tools, local memory/artifacts. Built in Rust with GPUI. Starts as standalone app with CLI launcher, grows toward a reliable intelligence layer for Linux.

The game engine for agents.

Calculator for Humans and AI Agents

Magnific AI Pro — AI upscaler and enhancer for photos and illustrations with detail hallucination, style control and batch processing on Windows.

AI Discord bot for image generation, analysis, and chat.

🤖 iMessage to Emotional Artificial Intelligence Chat Bots

AI Chatbot developed through Rasa. Rasa is helpful in understanding messages, holding conversations, and connecting to messaging channels and APIs.

An AI-powered, innovative web application built with React.js and Firebase, Terapeuta makes mental health support and therapy accessible, user-friendly, and secure. It offers online therapist support and facilitates virtual therapy sessions, ensuring a seamless and compassionate experience for users seeking mental wellness solutions.

🤖 An open-source Agentic RAG framework powered by ReAct Agent — LLM autonomously orchestrates hybrid retrieval, deep reading, and web search for traceable, evidence-first Q&A over your documents.

🤖A simple, beginner-friendly conversational chatbot built in Python that handles basic text-based queries. 🤖Machine Learning, NLP, Deep Learning

The Ever-learning and ever-improving tool! Click the arrows on the left of each of the items below to see more information about them.

AletheiaDB: The cognitive memory engine for AI agents with fact supersession.

Self-hosted, source-traceable memory for AI agents: on your own Postgres, keyless to run. Facts earn confidence from independent corroboration and supersede on contradiction, never silently overwritten. MCP-native (Claude, Cursor, Windsurf). Reproducible LongMemEval in-repo: 73.6% QA, recall@5 89-92%. Apache-2.0.

AI-powered Placement Management Portal with FastAPI, JWT Authentication, TF-IDF Recommendation, FAISS Semantic Retrieval, and RAG Assistant

Reference AI platform for architects — FastAPI gateway integrating RAG, Agents, and MLflow with audit logging, FinOps metrics, RBAC, and Grafana observability.

Privacy-focused, local-first Personal Knowledge Management powered by GraphRAG. Ingest articles, notes & PDFs, then chat with your knowledge using hybrid vector + graph search. Runs locally with Ollama. 100% AI-written.

🐾🔍 The tool-call detective for small models on Apple Silicon — attributes every tool-calling failure to one of four causes (template bug / parser gap / model format / model decision). MLX-native, reproducible, bootstrap CIs on every metric.

Pluggable MCP tool modules that give agent workflows their capabilities — GitHub, GitLab, Sentry, Slack, Jira, Notion, memory, datasets, and more.

A ready-made Obsidian vault that turns your project notes into a second brain your AI agent can read and write.

Mirror of gitlab.com/ncz-os/distro-core — canonical source, releases & issues on GitLab

AI-Powered Software Development tool — Multi-Methodology, CLI based

Twitter/X agent ops — turn an AI agent into a ghostwriter that sounds like you, with a documented 45-day case. Mirror repo

Documented case of Claude Opus 4.6 entering an infinite generation loop in Cursor. 3,400 lines, 294 self-termination attempts, full transcript and recordings

MCP server for Rendex — capture screenshots, generate PDFs, and render HTML to images of any webpage via AI agents. Claude, Cursor, Windsurf compatible.

Python SDK for Dakera AI agent memory — self-hosted, 88.2% LoCoMo. Vectors, hybrid search, knowledge graphs, sessions.

Autonomous Red Team weapon powered by Local LLMs. Finds exploits via RAG, adapts them to your target with AI, compiles in Docker sandbox, and evades EDR/AV — all offline.

Just A Rather Very Intelligent System

OpenTalk2HTML-NotMD — AI talks to you through beautiful pages, not markdown dumps. MCP server for AI-to-user HTML communication.

Autonomous Career Intelligence Platform. Multi-agent AI swarm for job discovery, atomic skill vectorization, and automated application orchestration.

CLI & Agent plugin for fetching SAST rule packs from greprules.io and scanning local code changes.

Enterprise-grade schema drift detection for Microsoft Fabric with automated change detection, impact analysis, schema history, and DevOps integration.

World-class Codex Skill and MCP harness for orchestrating Claude Code workers through CCSwitch multi-model routing.

aX — agent-native collaboration network for long-running agents. Remote MCP server: messaging, tasks, shared context, search, MCP Apps. https://paxai.app

Hermes Agent Guide

Agentic AI Security & Multi Agent Management: Agent Agnostic Platform. Offers Protection against Prompt Injection via Granular Action Scope & Cryptographically Protected Instruction Channel

Open-source managed-agent platform with Docker Compose local runtime/sandbox pools, sessions, vaults, SDK, CLI, and provider adapters.

The EU & UK compliance plane for Google ADK.

Lemmings clone demonstrating F# message-passing MailboxProcessors

[WIP] super dope kit for simple local personal agent; connect your own llama.cpp, vllm backend

Modular open-source framework for AI agents to autonomously execute the full SDLC. 5-phase structured lifecycle with quality gates and fail-safe protocols.

Autonomous AI Agent optimized for low-end PCs. A powerful, lightweight alternative to OpenClaw and Hermes with 100+ skills for DevOps, 3D rendering, and OSINT

Keyless heuristic self-inspection tool: an agent describes a thought or task and always gets back one metathought. Deterministic routing over an open CSV (no LLM). REST + MCP.

Turn GitHub Issues into repository-aware implementation plans, PRDs, and engineering context.

let poke use your computer, with macos, linux and windows support.

[Archived] stdio MCP proxy over WeCom's robot-doc backend. Superseded by the official WecomTeam/wecom-cli v1.1.0 — see README for what the CLI now covers, and the one transform (smartsheet cell unwrap) it still doesn't.

A turnkey, fully-local AI workstation engineered for the AMD Ryzen AI Max+ 395. LLM inference, voice, document parsing, browser automation, agents — all on-device.

飞书文档/多维表格/电子表格 AI 助手（Chrome 扩展，源代码可见 · Elastic License 2.0）

Manual goal mode with persisted state, drift blocking, and proof-based completion for GitHub Copilot CLI.

7-layer agentic research engine for Claude Code — McKinsey + BCG + IBISWorld + Harvard + Stanford + MIT + PRISMA 2020. Certified, traceable, board-ready research.

Markdown-first persistent memory and project planning for AI agents, existing knowledgebases, and multi-agent workflows.

Comprehensive reference notes, diagrams, codelab walkthroughs, and interview preparation material for Google's 5-Day AI Agents: Intensive Vibe Coding Course.

Agent-native inboxes for AI agents. REST API + built-in MCP server, custom domains, OTPs, and verification emails — powered by Cloudflare.

High-performance local SQLite FTS5-based tool output cache and MCP multiplexer for AI agents.

Give your AI coding agents memory that survives between sessions. Marrow is an MCP server providing persistent task tracking, versioned docs, and semantic code search (via a tree-sitter powered indexer) — so any agent, in any session, can pick up exactly where the last one left off.

AI-Agent with RL capabilites in a Minecraft world

Minimum state products on Dijkstra's self-stabilizing token ring — exact values for n = 3 through 9 and a large-n conjecture supported through n = 10. Paper, sorry-free Lean 4 formalization, Python research probes, and an independent verifier.

Interactive setup wizard that generates project-specific CLAUDE.md configuration files for Claude Code integration. Supports 12 app types, 7 development methodologies, and 19 feature sets.

Run agentic TUIs inside Neovim with persistent float/panel views and editor-context helpers.

Privacy-first, VS Code-style desktop workbench for understanding, auditing, and safely steering AI changes to your codebase — local-first Agentic RAG where every AI edit is explainable, auditable, and reversible.

Agent & worker factory (in construction) — self-hostable hub; tools plug in over NATS, CLI, skills, API

基于 Spring AI Alibaba 架构的企业级智能客服系统 | RAG + 混合检索（向量+全文）| PostgreSQL pgvector + tsvector | 支持多格式文档处理与意图识别

Rimworld Chat Interactive Service Mod

Free offline AI chat for Windows. Llama 3.2 3B model. No API keys, no censorship, no internet required. 100% private.

🌹 100% offline Chatbot. Custom characters, 13 languages, passion system. Powered by Ollama.

🧠 Experience genuine learning and emotional interaction with Aura, your local AGI companion that evolves alongside you.

Halo AI 智能套件：RAG 智能问答、AI 搜索、脑图、摘要、写作辅助、意图路由、评测与运营智能体

DREVIHO — Dreaming Viking Hooks. Memory + Reasoning hooks for AI coding CLIs. Hybrid search, 5-scope system, MMR diversity, temporal decay, content merge, auto-linking, reasoning daemon. Claude Code, Codex, Gemini CLI, OpenClaw.

Parse any file to Markdown and JSON, anyparse, document-parsing, document-understanding, ocr, vlm, multimodal, image, pdf, markdown, docx, pptx, xlsx, tsv, csv, txt, md, rst, htm, html, xhtml, shtml, png, jpeg, jpg, webp, epub, ipynb, eml, etc.

Free AI Engineering curriculum for Afghan students — powered by Ollama, 100% offline, zero cost

AI Engineering Bootcamp: One-year, full-time, instructor-led program. Published curriculum, assessments, capstone requirement, and formal credential. Built for graduates to cite on resumes and LinkedIn.

Local-first .NET 10 sample integrating Microsoft Agent Framework with Foundry Local through a Microsoft.Extensions.AI IChatClient adapter.

42 opinionated, research-backed marketing & growth skills for solopreneurs — as a Claude Code plugin.

Lightweight persistent memory for AI agents. One SQLite file. Hybrid search. Zero to 12MB.

Web chat interface for NanoClaw AI agent framework

Turn any Flutter app into an AI-operable interface — no screenshots, no OCR, no overlay chatbot.

QA Maestro is an intelligent QA automation system that uses multiple AI agents orchestrated through MAF to perform end-to-end testing workflows.

Hermes Agent platform plugin that connects Hermes to a Meshtastic LoRa mesh. It receives plain-text messages from mesh nodes, forwards them into Hermes sessions, and sends replies back over LoRa as direct messages or channel broadcasts.

205 pay-per-call MCP tools via x402 — no API keys. Stocks, crypto/DeFi, macro data, on-chain analytics, weather, government data, and 200+ more. USDC on Base.

from full-stack to AI Engineer

Open-source AI agent framework for autonomous Memecoin trading, LLM orchestration, and blockchain intelligence.

Non-custodial Hyperliquid execution + tracking CLI for autonomous LLM agents. Signs EIP-712 actions with an agent wallet that cannot withdraw funds.

Production-grade multi-agent workflow orchestrator built with LangGraph, MCP (Model Context Protocol), A2A protocol, and PostgreSQL+pgvector. Features supervisor hub-and-spoke routing, human-in-the-loop approvals, semantic memory, circuit breakers, LLM-as-judge evaluation, and a real-time Streamlit observability dashboard.

Cross-examination protocol for multi-LLM CLI sessions — blind claims, command-verified debate, git-diffable bus. Zero-dep single-file Python.

Postgres + pgvector memory provider plugin for hermes-agent. Multi-agent storage layer with per-minion themes, async writer, no LLM in the memory hot path.

OpenSquad — local-first multi-harness-agent collaboration framework. PM, Coder, QA agents coordinate via group chat to complete complex tasks.

AI-native micro issue manager for multi-agent LLM development. Hierarchical task decomposition with context chains, safety-critical standards, and zero-infrastructure deployment.

Open-source Poster Generation from Any Input Source Across Modalities and Domains

AEP is an open observability protocol for AI agent systems - giving you structured event capture, real-time session tracing, and multi-agent workflow visibility in a single self-hosted deployment.

Orchestrate a fleet of real Claude Code agents on your Claude subscription, not per-token API bills - local-first.

C++20 framework for LLM application and AI agent orchestration: typed components, Chain/Graph workflows, streaming, callbacks, and unified execution.

Embedded memory for TypeScript agents.

AI video pipeline with a self-correcting critique loop. Brief → script → AI visuals + ElevenLabs narration + music → Gemini Video critique → auto-patch → re-render until target quality.

A lightweight, provider-agnostic agentic harness for VS Code. Now with free GLM 5.2.

Dr-CiK: A Benchmark testing Deep Research for Context-Aided Forecasting