Open Source

App: OpenClaw

OpenClaw Foundation

Featured

Open-source personal AI assistant that runs on your own machine and answers from WhatsApp, Telegram, Slack, iMessage and 25 other chat apps.

App: Cloudflare OS

Cloudflare

Featured

Open-source AI workspace you deploy into your own Cloudflare account: agent chat wired to company context, sandboxed app building, and policy guardrails.

App: Hugging Face

Featured

The open-source AI hub: over a million models, hundreds of thousands of datasets, and hosted demo Spaces.

App: BrowserOS neo

Felafax, Inc.

Featured

Free, open-source desktop browser that coding agents such as Claude Code, Codex and Cursor drive using your real logged-in accounts.

App: Cline

Featured

An open-source coding agent for VS Code and JetBrains that plans before it edits and asks before it acts.

App: VoiceStudio

Palash Deb

Featured

Open-source, fully local voice AI studio for macOS, Windows and Linux — voice cloning, voice design, dubbing, dictation and transcription in 646 languages.

App: Kilo Code

Featured

Open-source AI coding agent for VS Code, JetBrains and the terminal — 500+ models at provider cost, task-specific modes, parallel agents in isolated git worktrees.

App: Dograh

Featured

Open-source voice AI platform you can self-host — a visual workflow builder, bring-your-own STT/LLM/TTS models, telephony, and no per-minute platform lock-in.

App: Unsloth

Unsloth AI

Featured

Open-source desktop app to run, serve and fine-tune text, image, video and audio models entirely on your own machine.

App: OpenHuman

TinyHumans AI

Featured

Open-source desktop AI agent that builds a local, readable memory of your work, then orchestrates agent fleets and durable workflows on top of it.

App: Osaurus

Osaurus, Inc.

Featured

Native macOS harness for AI agents — any model, persistent memory, sandboxed execution and cryptographic identity, fully offline and open source.

App: Mastra

Featured

An Apache-2.0 TypeScript framework for building AI agents — workflows, memory, RAG and evals — with a local studio and an agentic software factory on top.

App: goose

Agentic AI Foundation

Featured

Open-source AI agent from the Agentic AI Foundation — a native desktop app, CLI and API that runs tasks locally with 70+ MCP extensions.

App: OpenHands

All Hands AI

Featured

OpenHands — the leading open-source coding agent platform, self-hostable or run in the cloud.

App: NobodyWho

Featured

Open-source inference engine that runs LLMs, vision and speech models fully on-device — no API keys, no cloud calls, from Swift to Godot.

App: Firecrawl

Featured

Turn any website into clean markdown or structured JSON — crawling, JavaScript rendering, and extraction in one API.

App: seendiff

Abhishek Iyer

Featured

A local, keyboard-driven diff viewer built for the huge changes coding agents produce - and it remembers what you have already seen.

App: PageIndex

Vectify AI

Featured

A vectorless RAG engine that builds a tree index of long PDFs and lets an LLM reason its way to the right section, with page-level citations.

App: SkillOpt

Microsoft

Featured

Microsoft's open-source optimizer that trains an agent's SKILL.md like a model parameter — epochs, learning-rate budgets and a held-out validation gate, with frozen weights.

App: Toolport

Featured

Free, open-source local MCP gateway: register each server once, share it with every AI client, and cut tool-definition tokens by up to 91%.

App: Pi

Mario Zechner

Featured

Minimal, MIT-licensed terminal coding agent that adapts to your workflow via TypeScript extensions.

App: oMLX

Jun Kim

Featured

Menu-bar LLM inference server for Apple Silicon, with continuous batching and tiered KV caching that keeps local models fast enough for real coding work.

App: Cua

Cua AI, Inc.

New

Open-source computer-use infrastructure: a desktop driver, cloud desktop fleets, local macOS VMs and a benchmark for agents that click.

App: MCPJam

Featured

Open-source testing and evals platform for MCP servers — trace tool calls, debug OAuth, and catch cross-client regressions in CI.

App: Superagent

pungme

Featured

An open-source Mac app that gives Claude Code a real browser, a live iOS Simulator and its own git worktree per chat.

App: OneCLI

Featured

Open-source, sandboxed AI agents for every employee, fronted by a gateway that injects scoped credentials so the agent never holds a password.

App: Berd

Block

Featured

Block's open-source desktop workspace for AI agents — one native app for Goose, Claude Code, Codex, Copilot, Amp and Cursor.

App: OpenWorker

Andrew Ng

Featured

Andrew Ng's open-source desktop AI coworker that delivers finished work, not just chat replies.

App: Cactus

Cactus Compute, Inc.

New

8-29 MB automation models that run on phones, wearables and microcontrollers — tool calling, structured extraction and embeddings, fully offline.

App: OpenWork

Different AI

Featured

Open-source desktop app and MCP for running AI agents on your own files, an open alternative to Claude Cowork.

App: fx

Vercel Labs

Vercel Labs' tiny open-source coding agent: a ~6MB Zig binary that cold-starts in microseconds and embeds anywhere.

App: Arize AX

Arize AI

New

AI engineering platform for tracing, evaluating and improving LLM apps and agents — with Phoenix, its open-source local-first counterpart, for teams that want to start without a vendor.

App: aclif

Prompt One, Inc.

Open-source CLI framework that gives AI agents one command grammar across Salesforce, ServiceNow, DocuSign and Google Workspace, loading each schema only when asked.

App: OpenObserve

Open-source, OpenTelemetry-native observability platform for logs, metrics and traces — with first-class tracing for LLM calls and agent runs.

App: TablePro

Native, open-source Mac database client for 29 engines, with a Claude-powered SQL assistant and its own MCP server.

App: Oats

Ariso

Free MIT-licensed menu-bar meeting notetaker for Mac that can transcribe and summarise fully on-device, with no bot joining the call.

App: MagiCrew

Multi-agent workspace where teams hire reusable "digital employees" — an orchestrator runs specialists in parallel and returns finished decks, dashboards, reports and Excel files.

App: Roomote

Roo Code

Self-hostable cloud coding agent from the Roo Code team — investigates repos, verifies its own work and opens pull requests, driven from Slack, Teams, Discord or Telegram rather than an IDE.

App: LobeHub

Open-source platform for running a standing team of AI agents — you hire, schedule and review them, and they keep working while you are offline.

App: nanobot

HKUDS

Open-source, self-hosted personal AI agent you run yourself — browser UI, terminal or your chat apps, with memory, MCP tools and scheduled automations.

App: Feynman

Advait Paliwal

Open-source AI research agent with a CLI and a local science workbench for deep literature review, paper retrieval and replication planning.

App: Magnitude

Open-source local inference server that profiles your hardware, picks models that fit, and points your coding agent at them — free, private and offline.

App: Polygres

Evokoa

Turn a Postgres database into working memory for AI agents — relational rows, graph traversal and vector search fused into one ranked, token-budgeted context block.

App: Traccia

An OpenTelemetry-native control plane for AI agents that enforces policy mid-run instead of paging you after the incident, with cost attribution and EU AI Act evidence built in.

App: Playcall

Ibrahim Salami

Open-source call intelligence that scores sales calls against your own playbook and the buyer's context, not just what the rep said.

App: Vendo

Aisle Technologies, Inc.

An open-source layer that lets your customers describe a feature and get a working micro-app inside your product — sandboxed to their own permissions.

App: Lettertrace

Letter Company

Open-source, bring-your-own-key monitoring for how AI assistants describe your brand — track mentions across Claude, ChatGPT, Gemini and AI Overviews over time.

App: Meridian

Meridiona

An open-source work journal that records your day on-device and drafts the status update for you — nothing leaves the machine until you approve a worklog.

App: Munder Difflin

Chaitanya Giri

MIT-licensed multi-agent harness that turns the CLI coding agent you already use into a persistent clone of yourself, running around the clock.

App: Paritok

An open-source proxy that sits between your coding agent and the model, compressing tool schemas, file reads and stale history to cut token bills.

App: AgentMicro

fizzy718

Free, open-source macOS menu bar app that shows live status for every parallel Codex task, so you can see which agent needs you without reopening Codex.

App: OpenSEO

Every App, Inc.

Open-source alternative to Ahrefs and Semrush — keyword research, backlinks, rank tracking and site audits, billed by usage and exposed to agents over MCP.

App: MemoryCustodian

Zekun Wang

Open-source, repo-native project memory for coding agents, stored as plain Markdown.

App: Sim

Sim, Inc.

Open-source AI workspace where teams build, deploy and monitor agents on one canvas — visually or in code, across 1,000+ integrations.

App: E2B

Secure cloud sandboxes where AI agents can run untrusted code safely, starting in milliseconds.

App: Weaviate

An open-source AI-native database combining vector search, structured filtering, and built-in model integrations.

App: Qdrant

An open-source vector search engine written in Rust — fast, memory-efficient, and self-hostable.

App: Langfuse

Open-source LLM observability — trace, evaluate, and improve AI applications with production data.

App: LangChain

The framework and observability platform most teams use to build, debug, and ship LLM agents.

App: Browser Use

The open-source library that lets AI agents actually use websites — clicking, typing, and reading like a person.

Skill: WordPress Block Development

by WordPress

Featured

Official WordPress skill for Gutenberg block work: block.json, attributes and serialization, dynamic rendering, and the deprecation path that keeps existing content valid.

Skill: claude-mem

by thedotmack

Featured

Persistent cross-session memory for coding agents: hooks capture each session, a local SQLite + vector store compresses it, and a mem-search skill reads it back.

Skill: Gradio App Builder

by Hugging Face

Featured

Build Gradio web UIs and ML demos in Python with the current API — components, layouts, events, and chat interfaces.

Skill: GoLive

by mikehasa

New

Open-source agent skill that takes an AI-built app live on your own accounts: hosting, database, domain, email and payments, with a plan-and-approve workflow.

Skill: Dart Native Assets & C Interop

by Dart team

Compile C/C++ into Dart Code Assets with build and link hooks — local toolchain builds with linker tree-shaking, or hash-validated downloads of prebuilt libraries.

Skill: Dart CLI Application Architecture

by Dart team

The Dart team's skill for structuring real command-line apps — thin entrypoints, honest exit codes, stream routing, signal teardown and AOT-safe subprocess spawning.

Skill: Grafana Alloy Collector Configs

by Grafana Labs

Grafana's official Alloy skill: write one collector config that carries metrics, logs, traces and profiles, validate it locally, and prove samples are actually leaving the box.

Skill: Grafana Loki & LogQL

by Grafana Labs

Grafana's official Loki skill: write LogQL that returns rows instead of timeouts, ship logs through Alloy, and reason about a store that indexes labels rather than log text.

Skill: ROS 2 Engineering Skills

by dbwls99706

A single progressive-disclosure skill for production ROS 2 work — rclcpp/rclpy, colcon, QoS and DDS, tf2/URDF, ros2_control, Nav2, MoveIt 2, plus ROS 1 migration and hardware safety gates.

Skill: Robotics Agent Skills

by arpitg1304

Ten SKILL.md modules that give coding agents real ROS engineering judgement — ROS 1 and ROS 2, design patterns, perception, testing, Docker, bringup and robot security.

Skill: Paper Search Pro

by Bo

Multi-source academic literature search as an agent skill — OpenAlex, Semantic Scholar, CrossRef, PubMed and arXiv at four depths, from a 5-minute scan to a PRISMA-S logged systematic review.

Skill: Graphify

by Graphify Labs

Claude Code skill that turns any folder of code, docs, papers and images into a queryable knowledge graph, with every edge tagged as extracted, inferred or ambiguous.

Skill: GEO-SEO Analysis

by zubair-trabzada

Claude Code skill that audits a site for visibility in AI answers — citability scoring, AI-crawler access, llms.txt, schema markup and brand-mention scanning — plus classic technical SEO.

Skill: I Have ADHD

by ayghri

An output-style skill that stops a coding agent burying the answer: action first, numbered steps, state restated every turn, no preamble or filler.

Skill: Local Model Selection

by Hugging Face

Choose and run the right local model with llama.cpp and GGUF — quantisation, hardware fit, and local serving.

Skill: Hugging Face CLI

by Hugging Face

Hugging Face's official CLI skill — download, upload, and manage models, datasets, Spaces, and Jobs from the terminal.

MCP: ripwire

by Red Hat

New

Red Hat's zero-dependency C++23 code-context engine — ranked call graphs and blast-radius analysis, indexing a repo in under half a second with no server and no database.

MCP: Graft

by Trail

New

Builds a searchable markdown graph of your repo so coding agents stop re-exploring it on every task — reported 42% fewer tokens and 46% fewer tool calls.

MCP: AntV Chart MCP

by AntV

Featured

Official AntV MCP server that turns a description of your data into a rendered chart — 26 visualization types from bar and line to sankey, mind-map, fishbone and geographic maps.

MCP: Headroom

by Headroom Labs

Featured

Context-compression MCP server that shrinks tool outputs, logs, files and RAG chunks before they reach the model, cutting 60-95% of tokens on JSON payloads.

MCP: Engram

by Gentleman Programming

Featured

Persistent memory for coding agents as a single Go binary — SQLite and FTS5 behind MCP, an HTTP API, a CLI and a TUI, with no Node, Python or Docker required.

MCP: agent-device

by Callstack

Featured

Give a coding agent a live feedback loop on real mobile, TV and desktop apps — inspect, tap, type and capture evidence on iOS, Android and HarmonyOS over MCP or a CLI.

MCP: Nutanix V4 API MCP Server

by Nutanix

Featured

Nutanix's official open-source MCP server: 1,000+ Prism Central V4 API operations across 19 namespaces, read-only by default and audit-logged.

MCP: Hugging Face

by Hugging Face

Featured

Hugging Face's official remote MCP server — search and inspect models, datasets and Spaces, browse the Hub filesystem over hf:// URIs, and turn Gradio Spaces into callable tools.

MCP: Serena

by Oraios AI

Featured

Semantic code toolkit for coding agents — symbol-level search, editing and refactoring backed by language servers or the JetBrains platform.

MCP: Scrapling MCP Server

by Karim Shoair (D4Vinci)

New

Lets AI agents scrape the web through Scrapling, with HTTP, browser and Cloudflare-bypassing stealth fetches and CSS-narrowed, sanitized output.

MCP: Astro Airflow MCP Server

by Astronomer

New

Astronomer's MCP server for Apache Airflow: 30+ tools over the Airflow REST API, with consolidated helpers that explore a DAG, diagnose a failed run or summarise system health in a single call. Works with Airflow 2.x and 3.x.

MCP: CockroachDB MCP Server

by Cockroach Labs

New

Cockroach Labs' official MCP server exposes a CockroachDB cluster to agents as typed tools — schema inspection, cluster metadata, EXPLAIN and SELECT — with writes and DDL locked off unless you explicitly turn them on.

MCP: Fivetran MCP Server

by Fivetran

New

Fivetran's own MCP server exposes the Fivetran REST API to agents as discoverable tools, so an assistant can check sync status, inspect connections and destinations, and trigger syncs from chat.

MCP: x64dbg MCP Server

by duty1g

New

A native x64dbg plugin exposing 84 debugging tools and 22 event callbacks over HTTP, so an AI assistant can drive breakpoints, memory and disassembly directly.

MCP: OKF Agent Memory

by okf-memory

New

Git-native persistent memory for coding agents — sub-300µs BM25 search over version-controlled plain text, with no embeddings, no database and no API costs.

MCP: Payload MCP Plugin

by Payload

New

Payload's official MCP plugin — exposes every collection and global of a Payload CMS instance as MCP tools at /api/mcp, gated by Payload access control.

MCP: Unleash

by Unleash

Unleash's official MCP server for feature flags — and unusually, it first judges whether a change needs a flag at all before creating one.

MCP: Hugging Face

by Hugging Face

Hugging Face's official MCP server — search the Hub's models, datasets and Spaces, read repository files, and call thousands of Gradio applications as tools from one remote endpoint.

MCP: Mantine MCP Server

by Mantine

Mantine's official documentation server: gives an agent the component list, per-component docs and the exact props table, so generated React code matches the installed version.

MCP: tinymcp

by Golioth

Golioth's experimental MCP server that lets an LLM drive real embedded devices — device RPCs become MCP tools, with schemas stored in LightDB State and calls routed through the Golioth cloud.

MCP: ROS MCP Server

by robotmcp

Drive real robots from an AI assistant. Bridges MCP clients to ROS 1 and ROS 2 through rosbridge — publish topics, call services, send action goals and read sensors with no change to robot code.

MCP: Docs MCP Server

by arabold

Self-hosted documentation retrieval for coding agents — index any library's docs from the web, GitHub, npm, PyPI or local files and query them by exact version. An open-source Context7 alternative.

MCP: CVE MCP Server

by mukul975

Vulnerability triage for AI agents: 28 security tools across 24 free intelligence sources — NVD, EPSS, CISA KEV, MITRE ATT&CK, Shodan and VirusTotal — behind a single triage_cve call.

MCP: Cal.com MCP

by Cal.com

Cal.com's official MCP server: book, reschedule and cancel meetings, manage event types and schedules, and query real availability from a chat client.

MCP: agentmemory

by rohitg00

Self-hosted persistent memory for coding agents: hooks capture what you do, and an MCP server lets any agent recall it across sessions and across tools.

MCP: VoiceStudio

by Palash Deb

Local speech MCP server bundled with VoiceStudio — generate speech, clone a voice from reference audio, and transcribe in 646 languages, all on your own machine with no API key.

MCP: Burp Suite MCP Server

by PortSwigger

PortSwigger's official Burp Suite extension exposing proxy history, Repeater and scanning to AI agents over MCP.

MCP: Alpaca MCP Server

by Alpaca Markets

Alpaca's official MCP server for trading stocks, options and crypto, plus market data and portfolio analysis, in plain language.

MCP: Strapi MCP Server

by Strapi

Built into Strapi 5.47+, this MCP server turns your own content types into agent-callable tools — CRUD, publish and draft control, scoped by Admin token permissions.

MCP: Trigger.dev MCP Server

by Trigger.dev

Trigger.dev's official MCP server — trigger and monitor background jobs, deploy to any environment, and query runs with TRQL from your coding agent.

MCP: Backlog MCP Server

by Nulab

Nulab's official MCP server for Backlog — let an agent read and write projects, issues, comments, milestones, wiki pages, Git repositories and pull requests through the Backlog API.

MCP: MCPJam Inspector

by MCPJam

Testing and evaluation workbench for MCP server authors — inspect tools and prompts, debug OAuth step by step, and score behaviour across 16 client configurations before shipping.

MCP: Appwrite MCP Server

by Appwrite

Appwrite's official MCP server exposes databases, users, teams, functions and storage as agent tools, over a hosted OAuth endpoint or a local stdio bridge.

MCP: Arize Phoenix MCP Server

by Arize AI

Official MCP server for Arize Phoenix: read traces and spans, manage prompt versions, and run and inspect datasets and experiments from an AI assistant.

MCP: Couchbase Guru

by Couchbase

Couchbase's documentation agent as a single MCP tool: ask a question about any Couchbase product, SDK or version and get an answer with source links. No cluster and no credentials.

MCP: Anki MCP Server

by AnkiMCP

Turns Anki into a conversational tutor: 42 tools for reviewing due cards, rating them, creating notes and decks, and managing media over AnkiConnect.

MCP: Canvas MCP

by Vishal Sachdev

Connects AI assistants to Canvas LMS with up to 101 tools covering assignments, grading, analytics, discussions, accessibility auditing and course structure.

MCP: Equibles

by Equibles

Self-hosted financial data MCP server exposing 64 tools over SEC filings, XBRL financials, 13F holdings, insider and congressional trades, FRED and CFTC data.

MCP: Time

by Model Context Protocol

Time and timezone utilities — get the current time in any timezone and convert between zones.

MCP: Everything

by Model Context Protocol

A reference/test server that exercises every MCP feature — prompts, resources, tools, and sampling — for building and debugging clients.

MCP: Sequential Thinking

by Model Context Protocol

A tool for dynamic, reflective problem-solving through structured, revisable sequences of thoughts.

MCP: Memory

by Model Context Protocol

A knowledge-graph-based persistent memory system that lets an agent remember entities and relations across sessions.

MCP: Git

by Model Context Protocol

Read, search, and manipulate Git repositories — status, diffs, logs, branches, commits, and more.

MCP: Fetch

by Model Context Protocol

Fetch a URL and convert its contents to clean Markdown for efficient LLM consumption.

MCP: Filesystem

by Model Context Protocol

Secure local file operations for agents — read, write, search, and edit files within configurable allowed directories.