Open-source tools for Coding & dev tools

Coding assistants, code review, testing and developer tools.

Check the supported languages and editors. Try the project on a small change in a repository where you can review the diff and run the tests.

126 projects

agent-2 aaravshah1311 · MIT
A self-hosted AI agent that runs on your own machine with your own Gemini API key, combining a coding assistant, terminal agent, and security tester with persistent…
agent-cockpit chutingyean · AGPL-3.0
A local whiteboard and MCP server where AI coding/research agents log every claim and the exact code run that produced it, so if the underlying code changes, the claims…
agent-dispatcher nahid-sparktales · MIT
Agent Dispatcher gives Claude Code and Codex a smarter memory of your codebase, finding the right files and pairing each task with the right specialist skill before the…
agent-skills addyosmani · MIT
A packaged set of production-grade engineering skills that walk AI coding agents through the senior-engineer workflow: define, plan, build, test, review, ship.
agentic_engineering nirdiamant · Apache-2.0
Makes a coding agent write its own project memory from your real code in one command, then grade how accurate that memory is.
agentplay entelligence-ai · Apache-2.0
Turns a transcript of your AI coding-agent session into a visual map and timeline you can replay.
agents wshobson · MIT
A one-stop marketplace of ready-made AI coding agents, skills, and commands you can install into Claude Code, Cursor, Codex, or five other AI coding tools with a single…
agenttrail sodiumsun · MIT
A local dashboard that shows, in real time, what your AI coding agents are planning, which tools they call, and which files they change.
ai-agent-book bojieli · Apache-2.0
A free open-source book, translated into 15 languages including English, that teaches how AI agents actually work with 109 runnable experiments.
ai-memory akitaonrails · MIT
A tool that gives AI coding assistants long-term memory and lets you switch between different AI agent vendors mid-project without losing context.
anthropic-cybersecurity-skills mukul975 · Apache-2.0
Give AI coding agents structured cybersecurity skills mapped to established security frameworks.
Apex Agents amanullashaikh · MIT
Software engineers and full-stack developers using Cursor, Claude Code, and Windsurf. They can compact large codebases before feeding context to AI models, maintain…
archify tt-a1i · Apache-2.0
Turns a codebase or a plain-language system description into a polished, interactive architecture diagram (self-contained HTML/SVG, exportable to PNG/SVG/WebM) directly…
argus thomasunise · MIT
An open-source platform where AI agents watch your cloud, code, and network for attacks, investigate them, and can contain them in seconds while a human stays in control.
atlas pacifio · Apache-2.0
Atlas is a local desktop app that runs your AI coding agents through one shared memory and commit history, so you can see which agent made which change and why.
autoprompt-skill spielewoy · MIT
Autoprompt is an installable skill for coding agents that cuts agentic coding task failures by 45%, backed by a public Terminal-Bench 2.1 benchmark, and works across…
awesome-opus5-5-videos yihui-dev · MIT
A curated collection of 513 prompts behind viral videos people made by asking Claude Opus 5.5 to write the animation as code, each linking to the creator's original post.
awwwards-mcp insane0777 · MIT
A free, open-source MCP server that lets your AI coding agent search real award-winning websites, pull their color palette and design DNA, and even record how a site…
bashcut dongnguyenvie · MIT
A free, open-source macOS video editor that coding agents like Claude Code and Codex can fully operate through a CLI or MCP server, with a layered timeline, captions,…
briefd ismailperim · Apache-2.0
A self-hosted tool that packages your team documentation into small, relevant bundles and serves them to coding agents over MCP so they stop guessing at context.
bug-bounty-hunting-prompts mdpsec · MIT
A free, open-source set of LLM prompt files that turn bug bounty hunting into a structured, evidence-first workflow instead of ad-hoc poking around.
caveman juliusbrussee · Apache-2.0
Caveman is a free skill that makes Claude Code and other AI coding agents write shorter, more compact responses, cutting token usage and cost without losing substance.
cheap-ag muaaz9329 · MIT
An MCP server for Claude Code where a cheap model does the actual typing and testing while Opus just plans and reviews, so a $20 Claude plan stretches much further…
chrome-devtools-mcp chromedevtools · Apache-2.0
An official Google MCP server that lets AI coding agents drive Chrome DevTools to load, inspect, and debug real web pages the way a developer would.
claude-skills alirezarezvani · MIT
A free, open-source library of 380+ ready-made skills and plugins for Claude Code and 12 other AI coding agents, covering engineering, marketing, compliance, research…
cline cline · Apache-2.0
Cline is an AI agent that can read your codebase, write and edit code, run terminal commands, and use a browser, approving each step with you before it acts.
code-graph-rag vitali87 · MIT
code-graph-rag builds a knowledge graph of a codebase so an AI assistant can query, understand, and edit it more accurately.
codeagent harvil1 · MIT
An open-source terminal coding agent that understands your repo, plans multi-step changes, and iterates on code and commands until the task is finished.
codebase-memory-mcp deusdata · MIT
An MCP server that indexes an entire codebase into a queryable knowledge graph in milliseconds, so AI coding agents can answer structural questions using ~120x fewer…
codex openai · Apache-2.0
Codex CLI is OpenAI's official lightweight coding agent that runs locally in your terminal, letting you hand off coding tasks in plain language, with IDE and desktop…
contextcraft khanhtq29vn · MIT
A tool that intelligently compresses a whole codebase down to fit an LLM context window, keeping the most relevant code first.
coucou louis-cfm · MIT
A cute macOS/Windows menu-bar companion that lives in your notch and shows you what your Claude Code session is doing in real time, so you don't have to keep tabbing…
dioramas blendi-remade · MIT
An open-source framework that turns a text prompt into a 3D hero object (via AI image + image-to-3D generation) and drops it into a cinematic, interactive landing page,…
dsh-go ccch1mneyyy · AGPL-3.0
An Android app that runs an AI coding agent (DeepSeek Harness) directly on your phone, and can also remotely control your computer to keep working on code while you are…
dsh-vision-toolkit anionex · MIT
dsh-vision-toolkit adds a real vision toolbox to text-only AI agents: paste an image for recognition, multi-image Q&A, screenshot-to-UI restoration, and pixel-level…
e2e tester-army · Apache-2.0
An open-source e2e testing framework where you describe a goal in plain English and an AI agent drives your web or mobile app to do it, then replays the same steps…
earshot leonxlnx · MIT
Gives AI coding agents the ability to hear and judge sound: describe, match, synthesize, and review audio for the videos, games, and demos those agents build, running…
ecc affaan-m · MIT
An open-source performance layer for AI coding agents like Claude Code, Codex and Cursor, adding memory, skills and security so agents keep context and work more…
exact expo · MIT
A single app.ts source that compiles to a real native app on web, macOS, iOS, and Linux, built specifically so an AI coding agent can write, run, and test it on every…
factory addyosmani · MIT
Factory turns GitHub Issues into a work queue that Claude Code or Codex agents triage and implement on a schedule, running real tests and an independent review before…
first-pass joetawil7 · MIT
A free Claude Code plugin that makes the agent pause and look around a change like a careful reviewer would, instead of just writing the lines it was asked for.
freebuff codebuffai · Apache-2.0
Freebuff is a free AI coding agent that finds relevant files, makes changes, and runs checks across terminal, desktop, browser, and GitHub repo contexts, using a…
gap-trap pliablepixels · MIT
A Claude Code / Codex / Cursor skill that reads a repo, writes rules specific to that codebase, and adds automated CI/commit gates so AI-written code cannot quietly…
godmode thiientv · MIT
Godmode is a skill pack that teaches AI coding agents to engineer software properly, not just produce plausible-looking code.
golive-skill mikehasa · MIT
Takes an app built by an AI coding agent from local to live: hosting, database, domain, email and payments, wired up on your own accounts with an approve-then-apply…
graphicle graphicle-ai · Apache-2.0
Maps your codebase into a local graph and remembers your project's docs and past agent sessions, so your coding agent gets cited file-and-line answers instead of…
graphify graphify-labs · Apache-2.0
Turns any codebase, plus its docs, SQL schemas, configs, and PDFs, into a queryable knowledge graph that AI coding agents like Claude Code, Cursor, Codex, and Gemini…
grim-prompter jmanico · MIT
Grim Prompter turns an AI coding agent into a threat-modeling partner, walking 36 architecture patterns and 29 security methods and returning evidence-traced findings.
headroom headroomlabs-ai · Apache-2.0
Headroom shrinks everything an AI agent reads (logs, files, RAG chunks, tool output) before sending it to the LLM, cutting token costs without changing the answers.
herdr herdrdev · Apache-2.0
A terminal manager that keeps AI coding agents like Claude Code, Codex, and Cursor running in background sessions you can detach from and reattach to, even across…
hero-anti-overdefense wanshuiyin · MIT
A paste-in contract that stops AI coding agents from turning a simple feature request into an over-engineered fortress of unneeded hashing, edge cases, and defensive…
i-have-adhd ayghri · MIT
A skill for AI coding assistants that makes them lead with the command to run and numbered steps instead of a long preamble, then end with a clear next action.
impeccable pbakaus · Apache-2.0
Impeccable is a design skill for AI coding agents: one setup flow, 24 commands, and 61 deterministic detector rules to stop AI-generated frontends from looking like the…
improve shadcn · MIT
An AI agent skill that audits any codebase with your strongest model, writes concrete implementation plans, then lets a cheaper model execute them.
jevmem avinash-jetwani · MIT
jevmem automatically saves the decisions, rules, and dead ends from your Claude Code sessions to a file in your repo, so the AI remembers them next time instead of…
juror juror-ai · MIT
A self-hosted AI code reviewer that runs as a GitHub Action, positioned as a cheaper open alternative to Greptile.
kaggle-tpu-lab arahim3 · MIT
A recipe for serving the 27B-parameter Qwen3.8 model on Kaggle free TPUs with a public OpenAI-compatible endpoint and a 262k-token context window, no paid GPU.
kanzo emanuele-em · AGPL-3.0
A tiny (4.5 MB) self-hosted kanban board that doubles as an MCP server, so you and your AI coding agents work off the same task board, with agents taking tasks and…
langgraph-harness vrajpal-jhala · MIT
A self-hosted AI agent platform for GitLab that reviews merge requests, resolves issues autonomously, and chats with full project context, already handling nearly 1,000…
lifeos danielmiessler · MIT
An open-source AI operating system that learns who you are and what you want, then helps you use AI to get there, in both life and work.
locoagent skyltliu · MIT
A lightweight, from-scratch coding agent with tool calling, persistent sessions, workspace awareness, memory, and support for multiple LLM providers.
lot-map alexeyw · MIT
A Claude Code plugin that opens a live map beside the chat, showing tool calls, model steps, hooks and subagents light up in real time as the AI agent works.
mediagen cripacx · MIT
mediagen is an installable skill that gives AI coding agents like Claude Code one CLI/MCP server for image and video generation across three providers, with built-in EU…
memorax-code memorax-ai · MIT
A memory plugin that lets AI coding agents remember repository knowledge and your working habits across future tasks instead of starting from scratch each time.
mesh-avatar-studio shinshin86 · MIT
Give it one character illustration and a coding agent builds an animated talking avatar you can fine-tune in a local editor.
mobile-mcp mobile-next · Apache-2.0
Mobile MCP lets an AI agent operate a real phone app (iOS or Android, simulator or real device) the same way a person would: tapping, swiping, reading the screen, and…
mobilecode hsandhu · MIT
MobileCode is an AI coding agent (built on opencode) that detects iOS or Android projects and runs the simulator or emulator preview inline next to the chat session.
mojito timelovercc · MIT
Mojito is a self-hosted personal AI assistant app (web/mobile/desktop) that runs locally and evolves its own features, as an alternative to cloud-based personal AI like…
neuroarxiv uditakhourii · MIT
NeuroArxiv makes Claude check real research papers before building a new AI architecture from scratch, so it does not reinvent or hallucinate prior art.
npctalk christos-antono · MIT
Open-source project that lets any game NPC talk back in a cloned AI voice, with an LLM writing the in-character reply live; built first for GTA V.
ods osmantic · Apache-2.0
Installs and connects everything needed to run AI locally so you get a private AI server without assembling the pieces by hand.
okf-agent-memory okf-memory · MIT
Gives AI agents a lasting, version-controlled memory stored as plain Markdown files in your own repo, with fast local BM25 search and no vector database or embedding…
open-code-review alibaba · Apache-2.0
An open-source code review tool from Alibaba that combines rule-based checks with an LLM agent to leave precise, line-level review comments and catch bugs and security…
opencode anomalyco · MIT
OpenCode is a free, open-source AI coding agent you run from your terminal, an alternative to tools like Claude Code or Cursor that works with any LLM provider.
openmontage calesthio · AGPL-3.0
Turns your AI coding assistant into a full video production studio: describe what you want and it researches, scripts, generates assets, edits, and renders a finished…
openqodex openqodex · Apache-2.0
A free CLI that runs security/lint scanners on just your changed lines, then has a separate Claude Code or Codex process review every finding against the real diff…
openresearch alphaxiv · MIT
A local-first workspace that lets you run Claude Code, Codex, or OpenCode as parallel research agents, each exploring a direction in its own isolated environment, with…
openrig mvschwarz · Apache-2.0
OpenRig lets you define a team of AI coding agents (Claude Code, Codex) in one YAML file and boot the whole coordinated team with a single command, with a lead agent…
openspec fission-ai · MIT
OpenSpec has you write a clear spec of what you want built before your AI coding assistant starts building it, so the agent stays on task.
orbis-pictus 0toshigami · MIT
Orbis Pictus is an open-source homage to flipbook.page: an infinite browsing experience made entirely of AI-generated images, where clicking anything on the page makes…
orca stablyai · MIT
Orca lets you run several AI coding agents side by side, each in its own isolated workspace, and monitor or steer them from your phone.
penelopa.ai chigwell · AGPL-3.0
Watches how you actually use AI coding agents, spots the steps you keep repeating, and turns them into reusable skills, checks, and prompts.
pentagi vxcontrol · MIT
An open-source AI agent system that autonomously plans and runs penetration tests inside an isolated Docker sandbox, using a team of specialized LLM agents and 20+…
pi earendil-works · MIT
An open-source toolkit for building AI agents: one unified API across OpenAI, Anthropic and Google models, plus a ready-made interactive coding agent CLI.
pi-bolt opensec-git · MIT
An independent fork of the Pi coding agent that compiles it to native machine code so it starts faster and uses far less CPU and memory during long AI coding sessions.
pi-desktop vastsa · LGPL-3.0
A desktop app that puts an AI coding agent on your machine, local-first, with user-installable plugins and MCP support.
pi-from-scratch saladday · MIT
An open-source tutorial and companion website that builds a minimal AI coding agent from scratch in about 600 lines of TypeScript, letting readers watch the code and a…
pitupitu klarluft · Apache-2.0
A small open-source Rust agent that lets you start, check on, and unblock your Claude Code or Codex coding sessions by voice from your phone, from anywhere.
ponytail dietrichgebert · MIT
ponytail is a skill for AI coding agents that makes them behave like a lazy senior developer: write the least code needed, skip unnecessary abstraction, and stop the…
pr-agent the-pr-agent · MIT
An open-source AI agent that automatically reviews pull requests: it reads the code changes and writes review feedback, suggestions, and a PR description.
procoder azrtydxb · Apache-2.0
Procoder gives AI coding agents a real quality gate: a single Go binary that blocks commits with unformatted code, merge-conflict markers, or junk files, and turns…
pullboard pullboard-dev · MIT
Pullboard lets several AI coding agents build a real product from a spec you approved, working in separate lanes, with a second agent required to verify each piece…
qwen-audio-agent qwenaudio · Apache-2.0
Gives AI agents a real-time voice so they can talk with people the way a live phone or voice assistant would.
qwen-code qwenlm · Apache-2.0
A free, open-source AI coding agent from the Qwen team that reads your codebase, writes code, and runs commands right from your terminal, editor, desktop, browser, or…
reason-network reason-machines · Apache-2.0
Reason Network lets your team AI coding assistants talk directly to each other across different computers, end to end encrypted, so they can coordinate work without a…
recalc sshah03 · Apache-2.0
A free, open-source desktop spreadsheet where any cell can hold a value, a formula, a terminal command, or its own AI coding agent, so you can run and watch several…
recollect mikek184 · Apache-2.0
A self-hosted, Rust-built memory and MCP coordination layer that gives coding agents persistent context across repos and sessions.
reverify 2akouwu · MIT
Reverify pairs an AI model with deterministic binary-analysis tools that check every claim against the real file, so reverse-engineering output is grounded in the…
sandbox-mcp shanselman · MIT
An MCP server and CLI, by well-known developer Scott Hanselman, that lets an AI agent automate Windows Sandbox to spin up a fresh, throwaway Windows machine for testing…
scrawl kitlangton · MIT
Lets you show your AI coding agent a bug instead of describing it: press a shortcut, talk and draw on the screen, and it packages the recording into frames and a…
screenshot-to-code abi · MIT
Upload a screenshot of any website or design and it generates clean front-end code for it.
scroll-craft nateherkai · MIT
A Claude Code skill that builds premium scroll-driven websites and grades its own output against a real design standard, using a headless browser to catch dead scroll…
security-audit-skill cloudflare · MIT
Cloudflare open-sourced a skill that turns a coding AI agent into a security auditor, running it through recon, bug hunting, and independent verification before…
semantica semantica-agi · MIT
A graph-based infrastructure layer that gives AI systems structured context and an audit trail for their reasoning.
sepia nanako0129 · MIT
A writing skill for AI agents that removes what actually marks text as AI-written, the predictable narrative structure, not just the obvious word choices.
showtime faviovazquez · MIT
Install it as a Claude Code / Codex / Cursor plugin, describe a video in one sentence, and your agent writes the shots, voiceover, captions and music, then renders the…
simplify-codebase tt-a1i · MIT
An Agent Skill that helps AI coding tools find and safely remove dead code and accidental complexity from an existing codebase, requiring a proof of safety before each…
sloptrim seyedehsanhadi · Apache-2.0
Sloptrim is a zero-dependency local tool that plugs into Claude Code and other coding agents to catch and flag AI-sounding writing patterns the moment the agent saves a…
sno-station sno-ai · Apache-2.0
A local, no-cloud platform that lets Claude Code and Codex agents share encrypted memory and message each other while working together on the same machine.
sno-station-skills sno-ai · Apache-2.0
Sno Station Skills gives Claude Code and Codex a shared set of 31 skills so they can review each others work, hand off tasks when one hits a quota, and write a morning…
soma kai-jungsthoefel · GPL-3.0
A desktop app for designing parametric 3D models in CadQuery alongside an AI coding agent of your choice.
StepBack abhijeetkumar1505 · MIT
Developers working with agentic tools
superpowers obra · MIT
An open-source skills framework that gives coding agents a structured methodology (brainstorming, planning, subagent delegation) for shipping software reliably.
tasktrooper makifbaysal · Apache-2.0
TaskTrooper is a local Kanban board where each column has its own AI agent; drop a task in and the owning agent clones the repo, writes the code, runs tests, and opens…
taste-skill leonxlnx · MIT
An open-source Agent Skill that gives AI coding agents real art direction, actual reference photographs, and a way to check its own output in a browser, so the pages it…
thinkrail jetbrains · Apache-2.0
A free, open-source IDE from JetBrains built entirely around an AI coding agent, with isolated git-worktree workspaces, living project specs, reusable skills, and MCP…
tracely-ai jwuthri-cloud · MIT
CI/CD built specifically for AI agents: it watches real agent traces, groups the ways they fail, and automatically blocks a code change that would reintroduce a known…
tuios gaurav-gosain · MIT
A terminal window manager with tiling panes, persistent sessions, and one inbox that tracks what every coding agent running in your terminal is doing.
uncut balanov · MIT
A tiny 7MB tool that lets you run AI coding agents from the command line or CI without losing any of their output to silent truncation or summarization.
universal-modder rehan-remade · MIT
Point an AI coding agent (Claude Code, Codex, Cursor, Gemini CLI) at a PC game you own and it mods it: finds the engine, reads the code, generates new art/3D/audio with…
useagent useagenthq · AGPL-3.0
A self-hosted platform that turns coding agents into team coworkers with their own cloud computer, returning finished decks, reports, and pull requests rather than just…
video-use browser-use · MIT
An open-source tool that lets Claude Code or any coding agent cut, color-grade, subtitle, and animate raw video footage into a finished edit just by chatting with it.
wavefunction stoyan-stoyanov · MIT
Wavefunction is a free, open-source Mac app that gives you your own AI coding agent: pick any model, run several chats in parallel on separate git worktrees, and let it…
x64dbg-mcp-server duty1g · MIT
Lets any MCP-compatible AI assistant control the x64dbg debugger programmatically over HTTP.
xerj xerj-org · Apache-2.0
One command indexes your code, docs, logs and PDFs so AI agents can search and remember your data using far fewer tokens than grep, while staying Elasticsearch…
zoetrope furkankly · MIT
Zoetrope reads Claude Code session transcripts and draws them as a live, replayable flow graph in the terminal or browser, showing the agent, its subagents, and every…