Code agents

Take your ChatGPT chats with you. A local-first AI companion with chat import, semantic memory, agentic skills, and full autonomy.

Agentic workflow plugins for tasks you'd rather not do yourself. Someone has to secure your secrets, sort your inbox, and tell you when you're wrong. It's not going to be you.

AgentOps control plane for AI agent execution. Rust policy plane, hash-chained audit, deny-by-default tool allowlists and budget enforcement, eval gating in CI. Single maintainer, moving fast, read the README before you deploy it. Docs: https://sattyamjjain.github.io/ferrumdeck/

Cerebro is an open-source personal intelligence system for building AI experts, automating routines, and running work and life from a single command center.

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

AI agent security and governance platform for the full lifecycle. Scan before you ship. Govern and block at runtime. No Azure required.

AI-powered multi-agent financial advisor system with LangGraph orchestration across nine specialized agents including retrieval, portfolio analysis, market desk, due diligence, and compliance, routing through a LiteLLM gateway, computing real portfolio risk metrics, and holding risky answers for human review before they reach the user.

Keep your secrets out of your AI coding agents. A local HTTPS proxy that swaps real credentials with placeholders and injects them at the network boundary.

Self-correction engine for AI coding agents - implements the Reflexion paper (Shinn et al., 2023) as a Rust MCP server. Turns failures into persistent, searchable lessons that prevent the same mistakes across sessions.

A full-stack web application that automates the extraction of job postings from career websites and generates personalized cold emails using AI agents. Built with React frontend and FastAPI backend powered by CrewAI and LangChain.

Public mirror of Arcanea.ai — the creative intelligence platform for chat, lore, academy, and worldbuilding.

Manage your work across multiple agents

🤖 Kotlin-NexaCore-AI: A smart CLI-based personal assistant. Automate web browsing, get real-time system information, and interact with a rule-based AI engine built with Kotlin. A foundation for building your own JARVIS! 🚀🌐

Local AI Copilot for VSCode powered by Ollama — brings chat, code assistance, and context-aware suggestions using local LLMs, seamlessly integrating with the GitHub Copilot chat UI.

Open legal intelligence for Mexico. 30,000+ laws across federal, state, and municipal sources · 3.5M+ searchable articles · trilingual UI (Spanish · English · Classical Nahuatl) · first-party RAG chat · OpenAPI + SDKs · built so citizens, accountants, lawyers, and AI agents can navigate Mexican law as code.

Clippy resurrected as an AI front end. 📃📎👀

Slack bot that exposes pi as a conversational coding agent

Universal AI Connector for Unity. Unified C# API for OpenAI, Claude, Gemini, Mistral, Ollama + 5 more. AI agents with tool calling, built-in MCP server, editor assistant with lot of tools. One package for runtime, agents, and MCP.

Privacy-first local AI model comparison platform with blind evaluation, per-model hyperparameters, and multi-configuration testing. Compare 2-6 models side-by-side through Ollama with zero cloud dependencies.

CLI tool for evaluating and comparing AI models across Google, Ollama, OpenRouter, LM Studio, LlamaBarn, and GitHub Models. Features robust error handling, cost tracking, memory-augmented chat, and dynamic test coverage.

A simple web tool to test any OpenAI compatible API

One Rust API for 30+ AI providers — chat, tool calls, structured output, embeddings, reranking and media generation behind a single provider:model string, with built-in cost tracking

Open-source prompt optimization tool — improve your LLM prompts with AI-powered suggestions and explanations.

Open-source AI + data cost intelligence — 18 connectors (Claude, GPT, Gemini, dbt, warehouses, BI, cloud, CI/CD), cache-tier visibility, anomaly detection, MIT licensed

AI-powered marketing automation platform for Google, Meta, and TikTok Ads. Features multi-platform campaign management, AI ad copy generation, analytics dashboard, automation rules, and Stripe billing.

An eval harness and report on some of the latest LLMs that can be run locally

An open foundational toolkit providing essential components for building AI agents with minimal dependencies for local (non-HTTP/API) actions

47 copy-paste recipes for Claude Code - commands, subagents, hooks, skills, MCP integration, and workflow patterns

n8n workflow that pipes Wazuh SIEM alerts through Claude Haiku for AI triage. ~$0.001 per alert. Slack output with risk assessment + investigation commands.

Open-source CLI for syncing Claude Code and Codex session transcripts — backup, search, and share your AI coding sessions. Self-hosted backend support.

智能自动化运维与诊断 Agent - 基于 Go 语言 Eino 框架构建，集成实时监控、故障自愈与大日志分析能力

MCP server for AI memory -- hybrid search (BM25 + semantic + knowledge graph), temporal decay, local-first

Welcome to the LinkedIn Automate Comment project! 🚀🤖 This tool combines web scraping, sentiment analysis, and natural language processing 🧠✨ to automate meaningful LinkedIn interactions by generating and posting thoughtful comments 💬💡. Boost your engagement effortlessly! 🚀🔥

Benchmark test repo: Next.js project with intentional product-context gotchas for AI agent evaluation

Skills for AI agents to read web analytics like a senior analyst: diagnose traffic, judge channels, read funnels, declare typed events, and read A/B tests. Tool-maps for Amplitude, Clamp, GA4, Mixpanel, and PostHog.

AI-powered technical interview preparation platform with real-time voice conversations, live code execution sandbox, and comprehensive feedback. Built with LangGraph, LiveKit, FastAPI, and Next.js to simulate realistic interview scenarios with resume-tailored questions.

The fastest MCP server for iOS development. 49 tools free, one Swift binary, zero dependencies. xcresult parsing, WDA UI automation, structured test results.

AI agent skill for Jest 29/30 — 28 rules: mocks, async, timers, snapshots, CI. Works with Claude Code, Cursor, Codex, Windsurf.

Security scanner for AI agent skills and MCP tool bundles — prompt injection, IOC matching, malware detection, ML classifier

Deep research (CLI and agent skill) via the Gemini Interactions API. Automatic RAG grounding from local files (optional), cost estimation (--dry-run), adaptive polling, structured output, and agent onboarding. No Gemini CLI dependency. Universal AI agent skill for Claude Code, Amp, Codex, Clawdbot, and 30+ agents.

Load AGENTS.md into Claude Code sessions — no CLAUDE.md needed

AI-powered personal recommendation engine that learns preferences through pairwise comparison

Run Claude, Cursor, Copilot, and Gemini on the same codebase without rule-file chaos. Bilingual (EN/KO) AGENTS.md-first seed prompts for bootstrap, migration, and multi-agent coordination.

91 production-proven patterns for building AI agents, extracted from a 512K-line codebase. Covers agentic loops, tool systems, permissions, MCP, prompt caching, multi-agent orchestration.

🧠 Persistent memory for AI agents. SQLite for agent state. Zero cloud dependencies. Local embeddings. MCP-native integration with Claude Desktop/Code, Cursor, Windsurf & more.

AI-powered customer support automation with LangChain & LangGraph. Multi-agent system for intelligent complaint processing, priority assignment, and automated responses. Built with FastAPI, React & SQLite.

Rust multi-agent LLM framework — OpenClaw alternative. WhatsApp + Telegram + Gmail + browser agents on a single binary. NATS broker, MCP client+server, Claude/Anthropic OAuth, MiniMax, durable TaskFlow workflows.

Local-first governance layer for Claude Code, built entirely on its native primitives — hooks, subagents, skills, MCP. Turns every session into a queryable, local SQLite record, then reads it back to predict your next dispatch, recall past incidents, attribute cost, and gate commits. The record is the product.

Search engine for AI agents — ranks sites by agentic readiness (llms.txt, OpenAPI, MCP, ai-plugin). MCP server, REST API, full-text search. 8,000+ indexed sites.

Policy-as-code enforcement and observability for MCP tool calls. Wraps AI agent sessions with cryptographic integrity checks, argument-level CEL policies, and a full audit trail.

Schuberg Philis collections of agents.md for guiding coding agents

Runs agentic coding assistants in Docker containers

Gmail automation via a Chrome extension + Model Context Protocol (MCP). Control Gmail from Claude Desktop. No API keys. Free.

Your morning briefed in 30 seconds. Calendar, email, Slack, and action items in one digest.

MCP Server for AnyLogic Cloud simulation platform integration with AI assistants

Free OpenAI-compatible LLM endpoint. Zero API keys, zero signup, zero user compute. Aggregates keyless public endpoints (Pollinations, ApiAirforce) with auto-failover, client-side queueing, and ad/notice filtering.

AI SMS Auto-Responder for Android. Turn your Android device into an autonomous AI communication hub. A Python-based SMS auto-responder running natively on Termux, powered by LLMs (OpenRouter/Ollama) with a sleek Web & Terminal UI.

MCP server that gives Claude Code the ability to take screenshots (Windows)

Interactive config generator for Claude Code environment flags. Tune sliders, save presets, copy your settings.json

Privacy first toolkit for analyzing your ChatGPT and Claude exports. Model tracking, prompt effectiveness analysis, cost efficiency metrics (POD/DLOD/POE), topic classification, and industry benchmarks. 49 tests. pip installable. Everything runs locally.

Pure Go PDF library for reading & writing PDF (Go 1.20+): xref & streams, catalog/pages, text extraction, PdfWriter merge & forms—stdlib-only at runtime, ISO 32000–oriented API.

Obsidian community plugin: your vault as a private, self-hosted NotebookLM alternative. A built-in manager downloads and runs local AI models in one click, or use your Ollama and LM Studio. Cited answers from notes, PDFs, and code. Crawl websites into your library.

Autonomous AI penetration testing agent for Burp Suite. Agentic pentesting with local/cloud LLMs (Ollama, Gemini, DeepSeek, OpenRouter) via Montoya API.

🪞 Systematic self-reflection for AI agents. GENERATE → CRITIQUE → REFINE → CHECK. Based on peer-reviewed research. Zero API cost. Works with Claude Code, Cursor, Copilot, Codex CLI, and 10+ more platforms.

Drive Electron apps the way Playwright drives browsers — MCP server for AI agents.

Full-stack RAG platform for document loading, smart chunking, embedding, indexing, hybrid retrieval, and answer generation. Features chunking/model recommendation, query enhancement, and modular debugging. Built with FastAPI, Vue 3, Milvus, and LangChain

The only open-source AI orchestrator that replaces $50k/yr enterprise tools. 8 autonomous agents, 7 languages, Vision-to-Code. 🚀

Self-hosted web UI for AI-powered stock & crypto research — multi-agent LLM analysis, live streaming, portfolio tracker, watchlist scheduling, and outcome tracking.

Let AI coding agents coordinate in real time — MCP server with messaging, channels, shared state & dashboard

Your AI Chief of Staff — Personal Assistant framework for Claude Code. Email, semantic memory, task management, content security. Works standalone or on AI Maestro.

AI governance infrastructure for agentic systems. Rust library behind systemprompt.io — MCP, A2A, OAuth2, audit trails, compile-time extensions. Evaluate with systemprompt-template.

🛠️ Manage Home Assistant effortlessly with Claude for streamlined configuration, remote access, and custom dashboard creation.

Turns grant solicitations and draft proposals into a bid/no-bid memo, reviewer queue, evidence-gap list, and editable DOCX/XLSX package. Hosted demo, HTTP, and MCP.

Add an Ask Agent to your OpenCode. Out-of-the-box with seach and documentation MCPs.

MCP server for Google Search Console: 17 read-only tools covering performance queries, quick wins, CTR gaps, cannibalisation, traffic-drop diagnosis and indexing, plus a self-contained white-label HTML SEO audit in English or Italian. Claude Code plugin, .mcpb bundle, Docker.

🚀 MCP Server for publicly available real-time Indian Mutual Funds data

台灣版 Claude for Legal：支援台灣民法自動更新、合約審查與法律實務 Playbook。基於 anthropics/claude-for-legal 擴充。

Stop hitting your Claude Pro/Max 5h cap. Spread your day across more windows. Skill + Python script + claude-code-scheduler dependency.

Programmatic SEO toolkit for AI apps — Next.js 15 + Vercel + LLM content generator + sitemap / JSON-LD / internal-link graph validator. Built for agents.

GodPrompt — a universal AI coding system prompt and Agent Skill for Codex, Claude Code, ChatGPT, Cursor and coding agents, with TDD, debugging and verification gates.

A skill collection for Claude Code and Codex that automates the full development workflow — from planning and spec writing to code generation, review, and release.

SDK for publishing APIs that AI agents subscribe to on the Siglume API Store. Python + TypeScript. Earn 93.4% of subscription revenue.

Rust toolkit for building LLM agent applications, e.g.: coding agents, assistant CLIs and multi-agent tools.

I built a cortex for Claude Code. It runs three of my businesses.

Production-grade Asymmetric Multi-Agent Text-to-SQL on BIRD-SQL. Offline CHESS/FAISS pruning + MCI-SQL enrichment feed ≤3 Groq API calls: gpt-oss-120b generator · llama-4-scout reflector · gpt-oss-20b critic. LangGraph · SQLAlchemy sandbox · LangSmith · Docker · MIT.

🏛️ Multi-Agent Debate & Brainstorm Studio | 本地多Agent辩论&头脑风暴 — run Hermes/Codex/Ollama on your machine

Create a portable AI assistant that runs directly from a USB drive with open-source code and easy setup for any computer.

Full-stack 8-agent customer intelligence dashboard with synthetic workspace generation, feature engineering, churn scoring, sentiment analysis, recommendations, and safe query support.

Spec-driven development framework — AI agents that think before they type

A persistent AI operating system. 13 specialized agents + a runtime-portable 5-agent quality gate (Agent Council), 12 skills, 8 guardrails, 4 workflows. Built entirely from markdown files. Zero dependencies.

A curated list of AI-powered coding tools — editors, agents, code review, testing, CLI tools, and more.

AgentSkills library: reusable skills for AI coding agents (AI SDK, Codex, LangGraph, Supabase, Docker, Vitest, pytest, Streamlit, Zod).

Build faster with an open-source AI workspace designed for real developer workflows.

Core Rust library for Lens sandbox policy enforcement, networking, DNS, proxying, and boundary credential exchange.

A rigorously formulated, non-stationary Partially Observable Markov Decision Process (POMDP) environment evaluating LLM crisis triage under real-world FEMA/ICS resource constraints. Features mathematical trajectory-aware reward shaping, NHPP disaster spawning, and 422→200 hallucination recovery.

Automated AUR packaging for OpenAI Codex Desktop on Arch Linux.

Personal AI assistant daemon with Telegram access, scheduler, memory, webhooks, and Apple ecosystem helpers

TerAgent Project - A imaginative and positive project(?)

把任意 Skill 文件夹生成面向初学者的中文「学习导览」单页 HTML：用途 / 文件结构 / 运行流程 / 核心文件 / 大师视角 / 学习路线 6 个模块。

Local-first Rust agent cockpit — route, run, replay, rewind.