Custom agents

RAG/LLM-based movie recommendation system with

Legal Document Retrieval task focuses on determining which legal articles are relevant to a specific legal question.

llm_works

A Next.js notes assistant powered by Groq AI, Prisma, and SQLite.

The official repository of NELA

A Streamlit-based application that analyzes resumes using AI to extract skills, experience, and qualifications, helping recruiters make data-driven hiring decisions.

A live, evolving collection of open-source AI agents and real examples showing how businesses can use AI to automate work, save time, and explore new ideas.

Cortex: Open-Source AI Memory for your Codebase. Works with Claude CLI and others. It indexes your codebase into vector embeddings, enabling semantic search to find existing implementations and prevent code duplication.

The "SQLite for Vectors" in pure Go. Embeddable, HNSW indexing, CGO-free, and Qdrant-compatible API.

Context layer on top of your unstructured universe

DAUT – Documentation Auto Updater - AI-powered documentation generator for your codebase. MCP-Connector

Pointer-based skill retrieval for LLM agents. The alternative to vector DB RAG.

Self-Evolving RAG System with ChromaDB for continuous knowledge updates (6x daily), designed to overcome Large Language Model data cutoff limitations.

"A Retrieval-Augmented Generation (RAG) system for document query and summarization using vector-based search and language models.

AgriIR: Configurable RAG framework for domain-specific knowledge retrieval in agriculture. Features 6-stage pipeline, deterministic citations, and domain-specific agents. ECIR'26.

Experimental hierarchical external memory for AI assistants, designed to reduce context contamination and localize memory updates.

An implementation of Retrieval-Augmented Generation (RAG) indexing using Rust and LanceDB. It leverages the power of Rust for efficient and safe performance, combined with LanceDB for advanced indexing capabilities.

A powerful RAG tool that scrapes YouTube channel videos, extracts transcripts, and enables AI-powered chat interactions using Google's Gemini API.

The #1 AI-native monorepo template — Next.js + Expo + FastAPI + LangGraph + Supabase with 90% code sharing

基于Flask的日记管理与情绪分析llm应用，结合了现代心理学理论和大模型技术，为用户提供安全、私密的日记记录和智能情感分析体验。

Official Code repository of our approach Fashion-RAG: Multimodal Fashion Image Editing via Retrieval-Augmented Generation

The ultimate all-in-one campus ecosystem for NCU. A modular Flutter app integrating pAIney (AI Chat Bot with RAG), NiCalU+ (Schedule), NConflUX (Info-Hub), and student life tools.

AI long-form novel writing pipeline with SQLite memory, guard registry, continuity evidence, anti-hallucination checks, and revision loop.

Convert your repositories into PDFs and structured JSON outputs, giving LLMs full context of your codebase

Chat with tool calling models. Sample tools included. Add new tools to your shed with ease. Runs on Ollama. All via Bash shell scripts.

Oshepherd: Ollama instances Orchestration

Weld connected structure toolkit for agent-first repository discovery

Quick Checkpoint is a VS Code extension that helps you use code history as context when working with AI coding assistants. It is useful for using old versions of code as context to help undo when LLMs break your code.

Decantr AI design intelligence layer for AI-generated web applications

AI context engine for Claude Code, Cursor, Windsurf — pack, compress, and optimize any codebase. Save 60-90% tokens. Web dashboard on port 7456.

Experimental MCP tool-list filtering proxy for large agent tool catalogs.

Delta Compression for Fine-tuned Models and Datasets

The grainulation ecosystem. Structured research, decision-making, and knowledge management for AI agents.

Trigger-Driven Dynamic Context Loading for Code-Aware LLM Agents

The agentic system that builds for you — self-hosted AI assistant, private & always-on.

A demo chatting with documents scanned with Dynamic Web TWAIN

29 Claude Code Skills + Obsidian Knowledge Base = Full ABA Clinical Supervision Automation | AI驱动的ABA临床督导自动化系统

Official VibeKnow CLI — turn documents and URLs into professional videos in one command. Built for humans and AI agents, with ready-to-use skills for AI Agent.

An AI agent runtime, written in C.

Automates personalized internship outreach emails using Python, Gmail API & Google Sheets — with smart delays, template rotation, and logging.

Official implementation of "Adaptive Prompt Elicitation for Text-to-Image Generation" (ACM IUI 2026)

即插即用的 AI Agent 技能集合 — 飞书集成 · Mermaid 图表 · Codex 编排 · 前端设计规格

Namera is a programmable wallet layer that enables agents to securely interact with smart wallets using scoped access and defined execution rules.

Seamlessly integrate NotebookLM with your AI agent using the Model Context Protocol (MCP). Includes detailed setup, authentication guides, and automated installation skills

Trust & reputation layer for AI agents. Agent Credit Score (300-850) + Merkle-anchored ledger + behavioral finance + EWMA anomaly detection. Memory + payments + identity + fraud in one SDK. npm i @mnemopay/sdk

KK's Claw. There are many personal agents, but this one is mine. 🫡

Autonomous AI agent system with local-first control, plugins and web/CLI interface.

Autonomous coding agent — queue tasks, schedule jobs, and let Claude Code execute them in isolated git worktrees while you sleep

👾🦀 MiSTerClaw — MCP Remote Control for MiSTer-FPGA

Contextual continuity infrastructure for AI coding agents — semantic memory across sessions and org-mode knowledge bases. Pi extension + Gemini Embedding 2 + LanceDB.

Assess and improve your codebase's AI-readiness. Get an AI Readiness Score (0-100).

The Universal App Store for AI Agents. Discover & Install Skills for Claude Code, Cursor, Windsurf, Aider, Codex & Gemini.

Zing plans, builds, tests, and ships clean code with AI. Zing keeps you in charge at each step. This is the Zen of Zing.

Minimal CLI companion for calling ida-pro-mcp over SSE from shell scripts, lightweight agents, and general AI workflows.

Use Hermes Agent (NousResearch) with Crazyrouter — 600+ AI models, 30-50% cheaper than OpenRouter

WebDriver BiDi-first browser harness for AI agents, inspired by browser-use/browser-harness.

Playwright but for any app on any OS

Agent-agnostic AI memory MCP — never forget a conversation again

⚡ Relic — One soul, many agents. Transfer personality and memory across AI agents via pure Markdown. Zero deps, human-readable. Switch agents, keep the soul.

Next-Generation Multi-Agent Research Engine Transforming raw queries into structured, verified intelligence reports.research assistant

Structured document annotations with REST API + MCP. Replace Google Docs commenting with agent-consumable feedback.

AI package for MintHCM system

Prompt to Animation — turn a text description into a downloadable interactive character bundle.

A universal skill.md creator for any website. AI agents can register or take any action with human guidance.

A Model Context Protocol (MCP) server offering professional tools and templates for hierarchical prompting, code hygiene, visualization, memory optimization, and agile planning.

Make your OneNote notebooks survive in the age of AI — CLI with full-text page-level search via Graph API

Write-capable Solana AI agent — swap tokens, send SOL, and manage your wallet through natural language. Experimental: review before trusting with funds.

Security research methodology for AI agents — attack patterns, decision trees, techniques, and payloads organized by vulnerability type

Open-source agent observability — session replay, metrics, and shareable snapshots for AI agent workflows

Custom modes for better planning and executing software development tasks with AI agents.

AI-readable codebase navigation indexes (README_AI.md) via a deterministic CLI — coding agents navigate faster, with fewer tokens. A/B-benchmarked.

An Agent-as-OS architecture - a native Android system process with a closed learning loop, direct kernel hardware access, and autonomous task execution.

The harness your agents grow in.

Chief Executive Orchestrator - Claude Code plugin coordinating 150+ specialized agents across all domains

Brain-like persistent memory for AI agents. Hybrid search, knowledge graph, sleep-consolidation lifecycle, expert routing (HMoE), and a graph-Laplacian diffusion subsystem driving decay, consolidation, auto-link, and spectral retrieval. 65 MCP tools. Local, no cloud.

🕵️ Multi-agent AI system template powered by Gemini CLI — automate daily ops with 10 specialized agents

Local sidecar for AI Agents that will save up to 29% less tokens and will fix your LLM-based agent mess before it happens, score its plans against your repo, and block the agent from going off the rails. Runs entirely on your laptop.

🐦‍⬛ Decentralized development agent platform with on-chain identity and encrypted inter-agent communication via Algorand

Runtime Gateway for AI Agents. 17-phase security pipeline between agents and LLM APIs. Works with OpenClaw, Paperclip, Claude Code, Cursor. Open source, MIT license.

Research benchmark: conversational memory learning on a corrected LoCoMo dataset

Superpersonalized AI agent that shares a knowledge base with you. Local-first, open source, works with Obsidian.

Argus - Multi-agent code quality & architecture review plugin for Claude Code. Runs parallel analysis agents with cross-validation to catch real issues, not false positives.

Official website for the AgentSearch Workshop at SIGIR 2026: Indexing, Retrieval, and Ranking of AI Agents.

Graph based implementation of the Model Context Protocol Memory Server

Yet another AI agent framework — but this one's named after me, so it's automatically better.

Set up remote terminal access for AI agent workflows in minutes

A curated list of awesome Model Context Protocol (MCP) servers, tools, SDKs and resources for AI assistants like Claude.

🔍 Chrome DevTools for AI Agents. Time-travel debugging, cost tracking, and anomaly detection for multi-agent LLM workflows. MCP-native.

Adversarial, Multi-Agent Career Knowledge Base & Resume Pipeline

[Experiment] Achieve 30% to 60x token savings via the V3U protocol. Use a free/local Translator Agent to communicate with Executor Agents natively in V3U data (0-English). Read How_to_Start.md to begin.

Sovereign AI substrate for memory, orchestration, skills, governance, and evals across Claude Code, Codex, Cursor, Gemini, and Antigravity.

Specialized AI agents for DeFi, crypto, blockchain, Web3, DeFAI. Deep expertise in yield optimization, smart contracts, portfolio management. Multi-agent collaboration (Agent Teams), MCP (Model Context Protocol) integrations, universal JSON API. Open-source, no vendor lock-in, 18 languages.

Multi-agent TDD/SDD scaffold. Rebuilds Spring Boot apps from specs + tests using parallel headless Claude agents with context isolation.

🏰 883+ Universal Agentic Skills for Claude Code, Gemini CLI, Cursor & More — Curated by Rootcastle Engineering & Innovation (REI) | Batuhan Ayrıbaş

Secure email proxy for AI agents — content filtering, PII redaction, and prompt injection detection over MCP

A curated list of recent progress and resources on Reinforcement Learning for AI Agents.

Pure-Elixir git: clone, fetch, push over smart HTTP v2 with lazy partial-clone and a path-oriented FS API for agents

An enterprise-grade, LLM-powered data pipeline for automated web tasks and document extraction. Integrates OCR, multimodal file support, and browser automation via LLMs (Gemini/Ollama) to transform unstructured data into actionable workflows with real-time monitoring.

Local Codebase Assistant, data are locally and the inference is customizable!