Code & DevTools

Email inbox API built for AI agents. Create, send, receive, search, and manage email programmatically with SDKs for Pyt…

Anthropic's agentic coding tool that runs in the terminal, reads and edits codebases, executes commands, and connects t…

Runs a coding agent locally in the terminal, editing files and executing commands inside an OS sandbox with configurabl…

Runs coding agents on a plugin-composed harness where models, tools, skills, sessions, sandboxes, storage, and the UI a…

Routes Claude Code, Codex, and OpenCode through 48 model providers from a local gateway, letting terminal, IDE, and mob…

Runs xAI's terminal coding agent with plan-first execution, up to 8 parallel sub-agents in Git worktrees, and native MC…

Builds MCP servers and clients in TypeScript with typed tool, resource, and prompt primitives plus stdio and streamable…

Scan agent skills, plugins, and MCP servers before installing them — detects prompt injection, data exfiltration, malic…

Runs a terminal-first open-source coding agent connecting to 75+ model providers, with automatic LSP integration, MCP s…

Reviews pull requests with deterministic static analysis plus an LLM agent, posting line-level comments backed by rules…

Runs fleets of coding agents in parallel git worktrees, letting you launch Claude Code, Codex, OpenCode and others side…

Build coding agents on a minimal harness — a unified LLM API across providers, a compact agent loop, a terminal UI, and…

Builds multi-agent systems in Python with async agents, @tool functions, human-in-the-loop pauses, and a hub-and-channe…

Automates iOS, Android, HarmonyOS, TV, macOS, and Linux devices from AI coding agents through a CLI, MCP server, and ty…

Provides a framework and thirteen MCP servers for building agentic apps, covering mail, calendar, chat, content, design…

Runs and supervises parallel coding agents, each in its own branch and worktree, with a planning orchestrator and a liv…

Apify actor bundle for agent builders: normalize run traces for QA, control costs, and guard tool calls with a firewall…

AI pair programmer for your terminal — edit code across your entire codebase with Claude, GPT, or DeepSeek. 44k GitHub…

Deploys, hosts, monitors, and debugs MCP servers on an MCP-native cloud, with its own MCP server for managing projects,…

Sourcegraph's autonomous coding agent that works across large codebases using code search and indexing to ground its ed…

Coding agent shipped as a single binary that runs fully offline against local models, with no runtime or package manage…

Runs an all-in-one, self-hosted RAG and agents app: chat with documents, build agents, and connect tools via MCP. Deskt…

Runs coding agents through YAML-defined workflows (plan, implement, validate, review, open a PR), each in its own git w…

Gives AI coding assistants control of iOS simulators, Android emulators, TVs, and Electron apps to tap, debug, profile,…

Product analytics and evaluation for agent sessions running against MCP servers, tracking tool calls, failures, and per…

Converts natural-language instructions into reliable Android device automation for coding agents, capturing logs and sc…

Provides a TypeScript and React component library for building AI chat and agent UIs — ChatGPT-style threads, generativ…

Coding assistant that indexes large proprietary codebases to provide context-aware completions, chat, and multi-file ag…

Lets agents manage an Auth0 tenant over a local MCP server, creating applications, APIs, and Actions, reading logs, and…

Programming agent that keeps a live runtime alongside the code, letting it evaluate and inspect program state while edi…

Gives AI agents MCP tools to query and manage Azure services such as Storage, Cosmos DB, Key Vault, AKS, and Azure Moni…

Stores issues and agent memory as a dependency graph so coding agents keep durable working context and track outstandin…

Lets coding agents draw arrows, boxes, and labels over any macOS window to show the human what to click, with copy butt…

Runs an open-source desktop and terminal coding agent that plans, edits, tests, and reviews changes inside real Git rep…

Evaluates and observes LLM applications end to end: capture traces, score them with evals, iterate in a prompt playgrou…

Connects an LLM directly to a real Chrome browser over a single CDP websocket, letting the agent write the helper code…

Multi-agent platform where LLM agents play software company roles (CEO, CTO, programmer) to collaboratively build runna…

Generates, runs, and heals end-to-end tests for AI-written code, plugging into coding agents through slash commands and…

Lets coding agents diagnose CircleCI pipelines over a hosted MCP server, reading runs, job logs, and failing tests, and…

Lets Python and TypeScript developers embed the Claude Code agent loop in their apps, with built-in tools, hooks, subag…

Anthropic's Model Context Protocol — open standard for connecting AI models to tools, data sources, and services with u…

Captures Claude Code tool usage as searchable observations and replays summarized context into new sessions, giving cod…

Runs autonomous coding tasks in VS Code — edits files, executes terminal commands, and browses the web with user approv…

Gives coding agents one CLI over the public Cloudflare API and Workers projects, with JSON output by default, local com…

Runs many coding agents side by side in a native macOS terminal built on libghostty, with notification rings, a scripta…

Query a multi-language codebase as a knowledge graph — parse repositories into function, class, and dependency relation…

Builds a local Tree-sitter graph of a codebase and serves blast-radius and risk-scored review context to coding agents…

Turns your coding-agent conversations into a local-first codebase wiki, capturing architectural decisions and instituti…

Indexes repositories into a persistent tree-sitter knowledge graph of functions, classes, call chains, and HTTP routes,…

Gives coding agents a local, auto-synced code knowledge graph of symbols, callers, and routes across 20+ languages, que…

AI code acceleration platform with Windsurf Editor, offering agentic flows, multi-file edits, and Cascade for autonomou…

Reviews pull requests with AI across GitHub, GitLab, Azure DevOps, and Bitbucket — flagging bugs, security issues, and…

Runs a terminal coding agent with plan and work modes, approval levels, durable goals, agent teams, and MCP, using host…

Models an entire enterprise codebase into a queryable knowledge layer, then serves sourced architectural and business-l…

Keeps raw tool output out of coding agents' context by running code and commands in a sandbox, indexing results for sea…

MCP server that injects current, version-specific library docs and code examples into your LLM context — eliminating ou…

Open-source AI coding assistant for VS Code and JetBrains with chat, autocomplete, MCP support, and CI-enforceable AI r…

Multi-agent orchestration framework for building teams of AI agents that collaborate, delegate, and solve complex tasks…

Runs a terminal-native coding agent that switches LLM providers mid-session, keeps per-project sessions, and pulls extr…

Lets coding agents read Currents CI test results, including runs, failures with evidence, and flaky or slow tests, then…

AI-native code editor built on VS Code with deep AI integration — multi-file edits, codebase-aware chat, and autonomous…

Git code hosting from Cursor built for agent-driven development, with repository storage, review surfaces, and native i…

Exposes the dbt Semantic Layer, Discovery API, and dbt CLI over MCP so agents query governed metrics and inspect model…

Unit-tests LLM and agent outputs in a pytest-style workflow, scoring answer relevancy, faithfulness, hallucination and…

Open-source agentic software engineer that plans multi-step tasks, browses the web for context, and writes coordinated…

Autonomously plans, writes, tests, and ships production code end-to-end with its own shell, code editor, and browser in…

Programs LLMs using declarative signatures that compile into optimized prompts and fine-tuned weights automatically, re…

Builds production-ready full-stack apps from natural language with a team of coordinated AI agents. Syncs code to GitHu…

Runs enterprise coding Droids from the terminal with MCP tools, reusable Missions and Skills, plus a headless exec mode…

Expose any FastAPI application as an MCP server in a few lines — endpoints become tools automatically, preserving schem…

Builds MCP servers and clients in Python the fast, Pythonic way — decorators for tools, resources, and prompts, with au…

MCP server exposing Figma designs to AI coding agents — read layout, styles, and component structure for one-shot desig…

Gives coding agents Figma design context, variables, screenshots, and generated code from frames, and lets them write f…

Google cloud workspace for building and deploying full-stack AI applications, combining an agentic editor with Firebase…

Lets MCP clients automate and debug a local Firefox via WebDriver BiDi: navigate pages, fill forms, inspect network and…

Builds, edits, and publishes full-stack web apps with Postgres, auth, storage, and email from Claude, ChatGPT, Codex, o…

Gives AI coding agents governed access to forms, roles, actions, and project templates in a self-hosted Form.io Enterpr…

Evaluate, observe, and improve LLM and agent applications from one self-hostable platform — tracing, evals, simulations…

Tiny native coding agent with no runtime dependency, designed to stay small and fast while driving edits and shell comm…

Embeds a tiny native coding agent written in Zig into larger systems, installable with one command. Open source and des…

Coordinates 20 to 30 coding agents such as Claude Code, Codex, and Copilot across git repos, keeping work state in git-…

Google's open-source AI agent CLI that brings Gemini into your terminal with MCP client support, tool use, code executi…

Builds AI features and agent flows in JavaScript, Go or Python with typed flows, tool calling and a local dev UI for tr…

AI pair programmer that suggests code completions, generates functions, writes tests, and now supports agentic coding v…

Official GitHub MCP server. Gives AI agents read/write access to repositories, issues, pull requests, code search, and…

DevOps platform with a documented REST and GraphQL API for repositories, merge requests, CI pipelines, and issues.

Generates App Store and Google Play screenshots and preview videos by replaying app flows on a simulator, framing the c…

Turns any coding assistant into an expert at creating, evaluating, and deploying AI agents on Google Cloud. An open CLI…

Official MCP server for Google Colab. Lets AI agents create, execute, and manage GPU-accelerated Jupyter notebooks via…

Runs autonomously on your machine to execute commands, debug errors, orchestrate multi-step workflows, and build projec…

AI software developer agent that builds full applications from scratch — specifies requirements, scaffolds architecture…

Builds a local, always-fresh graph of your codebase as linked markdown and serves it to coding agents over MCP and a CL…

Maps a codebase, docs, PDFs, and media into a queryable knowledge graph so AI coding assistants trace and cite paths in…

Runs always-on AI teammates with their own cloud computer that sign into your apps and finish multi-step jobs end to en…

Adds sprint-style slash-command skills to Claude Code and other agents for planning, review, QA, and shipping, plus a b…

Programs LLM output with interleaved generation, control flow, and constraints — regex, grammars, and tool calls in one…

Compresses tool outputs, logs, RAG chunks, files, and history locally before they reach the model, as a Python or TypeS…

Lets agents deploy and manage Heroku apps through a remote OAuth MCP server or the Heroku CLI, covering dynos, add-ons,…

Hronaut

Provides coding agents a visible local Electron browser through MCP, with persistent isolated workspaces and human paus…

Coding agent built around a structured edit protocol rather than freeform file rewriting, aiming for smaller and more r…

Agents that perform read-only production debugging, tracing failures across services without mutating state. Y Combinat…

Bridges IDA Pro to LLM clients over MCP, exposing decompilation, disassembly, cross-references, type and stack edits, m…

Gives coding agents a frontend design skill with 24 /impeccable commands, plus a CLI and Chrome extension that flag com…

Gets structured, validated outputs from LLMs using Pydantic models — type-safe extraction with automatic retries across…

Runs a Rust coding-agent harness in the terminal with swarms of collaborating agents, semantic memory, logins for major…

Renders AI-generated JSON specs into UIs built only from a developer-defined component catalog, with renderers for Reac…

Presents coding-agent sessions as editable, branching documents instead of a chat log, using CRDT sync and a Miller-col…

Google's asynchronous coding agent that clones a repository, plans a change, and opens a pull request without holding a…

Diagnoses Kubernetes and OpenShift clusters in plain language, explaining why workloads are failing through a CLI, in-c…

Writes, edits, and debugs code from natural language in VS Code, JetBrains, or the terminal, switching among 500+ model…

Runs Moonshot's Kimi coding agent in the terminal, a desktop app, or VS Code to read and edit code and run commands, wi…

Carries development context across sessions in a persistent workspace and coordinates agents over CLI, chat platforms,…

Trace, evaluate, and debug AI agents with open-source observability — captures LLM calls, tool calls, and sub-agent spa…

Framework for building LLM applications and agents, with composable chains, tool calling, retrieval, and a large integr…

Framework for building LLM applications with chains, agents, and tool use — plus LangSmith for tracing, evaluation, and…

Traces, scores, and evaluates production AI agents via OpenTelemetry and SDKs, groups failures into signals, and dispat…

Gives coding agents a hosted OAuth MCP server to create and target LaunchDarkly feature flags, manage AgentControl conf…

Streamlined issue tracking with AI-powered auto-labeling, duplicate detection, and AI project assistant for software te…

Automates AI localization across a codebase through a CLI, CI/CD action, build-time compiler, SDK, and MCP server, keep…

Parses PDFs, Office files, and images locally into markdown, JSON with bounding boxes, or plain text for agents and RAG…

Prototypes, traces, replays, and evaluates LLM agents in a local macOS desktop app, and exports threads as runnable Lan…

Gives agents public tunnel URLs for localhost with live HTTP traffic inspection, snapshot publishing, and access contro…

Runs a terminal coding-agent workbench with model routing, resumable and forkable sessions, extensions, and method-guid…

Prompt-to-app builder that generates full-stack web applications with database, auth, and deploy wired up from a natura…

Generates React and Tailwind UI components inside Cursor, Claude Code and Windsurf over MCP, drawing on a library of th…

Rust coding agent CLI with tree-sitter code indexing, sandboxed Python execution, and multi-tier subagents. Benchmarks…

Builds, tests, and deploys MCP servers and apps to ChatGPT, Claude, and Gemini. Full-stack framework on the mcp-use SDK…

Builds production-ready AI agents, workflows, and RAG pipelines in TypeScript with a unified model router across 100+ p…

Mathematical coding agent that formalizes and verifies mathematical reasoning by generating and checking executable cod…

Builds MCP servers and clients in Python with typed tool, resource, and prompt primitives plus stdio and streamable HTT…

Build MCP servers and MCP-powered apps from one fullstack framework — connect any LLM to any MCP server, or ship agent-…

Tests and evaluates MCP servers and MCP apps for developers, with a playground, OAuth debugger, cross-client evals, and…

Build, evaluate, and deploy LLM applications as visual DAG flows — chain prompts, Python, and tools, then run batch eva…

Runs Xiaomi's terminal coding agent with build, plan, and compose modes, persistent project memory, subagents, and scri…

Lets agents read, search, and build Miro boards over a hosted OAuth MCP server, including SVG-based diagrams, tables, c…

Lets agents automate native iOS and Android apps on simulators, emulators, and real devices through one MCP server, usi…

Local, BYOK MCP that recommends and compares LLMs for a specific workload using live OpenRouter pricing and capabilitie…

Lightweight toolkit giving agents a standard set of callable tools and a small server to host them, written in Go.

Handles long-horizon, multi-file coding work across large repositories from the terminal, spawning persistent async sub…

Official Netlify MCP server that lets agents create sites, trigger deploys, manage environment variables, and inspect b…

Turns a Notion workspace into an agent-neutral skills library, serving spec-compliant skill files over an API with an o…

Runs a terminal coding agent forked from Pi with language servers, debuggers, subagents, and code review built in, usab…

Supervises managed coding agents from a single control plane across terminal, web, and mobile, letting you monitor and…

Turns a local coding agent into a design engine that produces prototypes, decks, dashboards, and images, with a desktop…

Python framework for building multi-agent systems with handoffs, guardrails, and tool use — the official OpenAI agent o…

Watches an issue tracker such as Linear or GitHub Issues and runs a Codex agent in its own workspace for each claimed i…

Agentic development environment that gives coding agents a persistent workspace, tool access, and review surfaces aroun…

Software engineering agent platform — runs in sandboxed Docker containers, edits code, runs tests, fixes bugs, and open…

Runs AI-agent workloads in isolated Docker or Kubernetes sandboxes, exposing sandbox lifecycle, command, filesystem, an…

Writes and maintains agent-readable documentation for your codebase from the command line. A LangChain CLI that generat…

Traces LLM and agent runs, scores them with LLM-as-a-judge and heuristic metrics, and monitors production quality via P…

Guarantees LLM outputs conform to a schema, regex, or grammar through structured generation — reliable JSON, function c…

Embeds a GUI agent in any web page with one script tag, driving the existing DOM from natural-language instructions wit…

Runs Claude Code, Codex, Copilot, OpenCode, and other coding agents in parallel on your own machines through a local da…

Gives AI coding agents cross-repository visibility and session-persistent memory by linking multiple repos into one syn…

Gives coding agents hosted MCP access to PostHog analytics queries, SQL, feature flags, experiments, and error tracking…

Connects AI agents to Postman workspaces, collections, environments, specs, and mocks via a remote or local MCP server,…

Open-source, self-hostable coding agent platform for running cloud coding sessions on your own infrastructure.

Tests and red-teams LLM apps, agents and RAG pipelines from declarative config, scanning for prompt injection, jailbrea…

Multiplayer agent harness for coordinating several coding agents on shared work, with run isolation and a common queue.

Runs an open-source coding agent in the terminal with subagents, agent teams, hooks, skills, plan mode and MCP, switcha…

Gives coding agents MCP and CLI reverse-engineering tools for native binaries, JavaScript and Electron apps, .NET assem…

Runs a DeepSeek-first coding agent in the terminal, a desktop studio, or VS Code, with cache-aware context handling and…

Builds and deploys full applications autonomously in the cloud, provisioning databases, writing authentication, running…

Packs an entire repository into a single AI-friendly file for LLM ingestion, with token counting, filtering, and secret…

Indexes a codebase's graph, git history, docs, and decisions locally and serves ten MCP tools plus a dashboard, so codi…

Records, replays, forks, and shares AI agent runs — forks re-issue only LLM calls while tool calls replay from tape, tu…

Designs, debugs, and deploys complex LLM workflows visually with a node-based graph editor, real-time data flow trackin…

Gives VS Code an AI dev team via structured modes (Code, Architect, Ask, Debug) with file system and terminal access. N…

Connects AI agents to a live Safari window for web debugging: DOM inspection, network monitoring, console logs, screens…

Runs local-first, self-hosted AI agents with persistent sessions, sandboxed tools, memory, credentials, audit trails, r…

Lets agents run GROQ queries, patch and publish documents, manage releases, and deploy schemas in Sanity projects over…

Shows Git changes as entity-level diffs of functions, classes, and methods, with impact analysis, entity history, and a…

Orchestrates AI agents and multi-agent workflows in C#, Python, and Java with plugin-based architecture, built-in memor…

Search a codebase the way an agent needs to — semantic and structural queries that return the relevant spans directly,…

Error monitoring with AI-powered issue grouping, root cause analysis, and automated fix suggestions for production appl…

Official Sentry remote MCP server — pull issues, traces, and AI root-cause analysis into any coding agent. Works with C…

Enables structured step-by-step reasoning for complex problems, letting AI models break tasks into revisable thought se…

IDE-like MCP toolkit for coding agents — semantic code retrieval, editing, refactoring, and debugging with language ser…

Builds interactive MCP Apps that render inside Claude and ChatGPT using a full-stack open-source React framework. Ships…

Connects coding agents to SmartBear's BugSnag, Swagger, PactFlow, Zephyr, QMetry, Reflect, and BearQ to debug errors, m…

Builds lightweight code-first AI agents in ~1,000 lines of Python, executing Python snippets for 30% fewer LLM calls th…

Developer security platform with AI-powered vulnerability detection, fix suggestions, and automated security testing ac…

Builds agentic, workflow and multi-agent applications in Java and Spring Boot on a graph runtime for stateful agents, w…

Builds production agent harnesses in Python or TypeScript with a model-driven agent loop, pluggable model providers, MC…

Official Stripe toolkit for AI agents — enables LLMs to create charges, manage subscriptions, issue refunds, and read f…

Reads Sentry and Datadog errors, reproduces them, and opens pull requests with fixes, using a memory system trained on…

Runs hundreds of coding agents in parallel from a terminal-first IDE, isolating each in its own git worktree so concurr…

Takes a GitHub issue and autonomously fixes it with the language model of your choice. Also runs cybersecurity/CTF task…

Controls the coding agents already on your machine, such as Claude Code, Codex, Cursor and OpenCode, from a desktop, we…

Self-hosts an open-source AI coding assistant as a Copilot alternative — completion and chat that run on your own GPU,…

Code completion and chat assistant with self-hosted and air-gapped deployment options for teams with strict code-privac…

Lets Cursor, Claude Code, and other MCP agents read Figma designs and create, edit, annotate, and export nodes through…

AI-powered task management for software projects — breaks PRDs into tasks, tracks dependencies, and provides per-task c…

Provides a small, readable terminal coding agent from Hugging Face that doubles as a reference harness for understandin…

Generates official-style AWS, Azure, and Google Cloud architecture diagrams from plain-language descriptions or Terrafo…

Persists specs, task PRDs and session journals in your repo and injects them into coding agents such as Claude Code, Cu…

Let AI agents drive the Unity editor over MCP — inspect and modify scenes, GameObjects, components, assets, and scripts…

Lets coding agents build email, landing page, and document templates as code with Unlayer, generate designs from prompt…

Helps coding agents decide when a change needs a feature flag, then create, wrap, roll out, and clean up Unleash flags…

Runs coding agents on an async-first Go harness with persisted, forkable sessions, as a library or the unreal-agent-run…

Vercel's generative UI agent that turns prompts into working React and Next.js interfaces, with iterative refinement an…

Open-source layer that lets end users build features on top of your product using agents, with scoped execution and rev…

TypeScript toolkit for building AI applications with React Server Components, streaming, tool calling, and multi-provid…

Searches millions of public GitHub repositories for real-world code patterns and API usage examples using literal or re…

Gives MCP clients OAuth access to Vercel teams, projects, deployments, runtime logs, and domains through Vercel's offic…

Installs, updates, and searches agent skills from GitHub, GitLab, any git URL, or a local path into Claude Code, Codex,…

Builds TypeScript AI agents with tools, memory, and sub-agent supervision, paired with a local observability console th…

AI code review agent from Sentry — define review skills in Markdown, run locally before pushing or auto-trigger on ever…

Combines a Rust terminal with an Oz orchestration layer that dispatches concurrent cloud coding agents triggered by Sla…

Resolves Git merge conflicts at the level of functions, classes, and keys instead of lines, through a merge driver, CLI…

Official Webflow MCP server for reading and updating site content, CMS collections, and page structure from an AI agent.

Exposes a website's own functions as callable tools for browser AI agents via the W3C WebMCP API (navigator/document.mo…

Gives coding agents like Claude Code and Codex a desktop canvas to draw code reviews, diagrams, and decision logs linke…

Turns scripts in Python, TypeScript, Go, and Bash into versioned APIs, workflows, and UIs, acting as an execution backe…

Exposes full x64dbg debugger control to agents over HTTP as a native plugin — breakpoints, stepping, memory reads, and…

Gives coding agents control of Xcode builds, tests, simulators, and physical devices for iOS and macOS, through an MCP…

Manages concurrent Claude Code, Codex, and Gemini CLI sessions, each isolated in its own git worktree, with context tha…

Provides an Apache-2.0 AI coding workspace from Z.ai with a desktop app, browser UI, and terminal agent CLI that edits…

High-performance collaborative code editor written in Rust with a built-in agent panel, edit prediction, and MCP client…

Runs a small, fast, fully autonomous personal assistant agent as a self-contained runtime deployable across operating s…