Open source · TypeScript
Best TypeScript AI agents
The 111 open-source AI agents written in TypeScript in this index, ordered by recorded GitHub star count, never by sponsorship. Stars are repository-interest signals, not performance or maintenance guarantees. firecrawl leads the set at 190,705 GitHub stars, and 88 of the 111 have a recorded repository push in the last 90 days. These records have TypeScript as their primary repository language and recognized open-source software licenses recorded in this index; check the current licenses, deployment requirements, and model or API costs. Right now it's led by firecrawl (191k stars), with gemini-cli and MCP Reference Servers following. Order follows the recorded star counts; repository activity is shown separately.
Fetcher MCPMCP serverFetch JavaScript-rendered web pages with a headless browser and return their main content as HTML or Markdown.Open sourceCosts not checkedTypeScript · recorded license: MITRecord checked 1.1kGitHub starsdao-codeAgentOpen-source TypeScript terminal coding agent for DeepSeek-V4 — builds on DeepSeek's strong price-performance and ultra-cheap cache pricing, engineering byte-stable prefixes and cache-reusing forks soOpen sourceCosts not checkedTypeScript · recorded license: MITRecord checked · Recent push 1.1kGitHub starsai-maestroFrameworkAI Agent Orchestrator with Skills System - Give AI Agents superpowers: memory search, code graph queries, agent-to-agent messaging. Manage Claude, Codex or any AI Agent from one dashboard.Open sourceCosts not checkedTypeScript · recorded license: MITRecord checked · Recent push 818GitHub starsparchiAgentYour AI friend right in your browserOpen sourceCosts not checkedTypeScript · recorded license: MITRecord checked · Recent push 551GitHub starsStarmoonFrameworkConversational AI device and software framework; upstream is deprecated.Open sourceCosts not checkedTypeScript · recorded license: GPL-3.0Record checked 548GitHub starsAsyncAgentIDE, A native-feeling AI coding workspace that blends chat, planning, agent execution, and project navigation into a unified desktop experience.Open sourceCosts not checkedTypeScript · recorded license: Apache-2.0Record checked 474GitHub starsDeepgram JavaScript SDKSDK / libraryJavaScript client library for Deepgram APIs; hosted service usage is separate.Open sourceCosts not checkedTypeScript · recorded license: MITRecord checked · Recent push 277GitHub starsgdansk-aiAgentFull stack voice chatbotOpen sourceCosts not checkedTypeScript · recorded license: GPL-2.0Record checked 199GitHub starsglanceMCP serverAI-powered browser automation MCP server for Claude Code. Navigate, click, screenshot, test — all from your terminal.Open sourceCosts not checkedTypeScript · recorded license: MITRecord checked 156GitHub starsCybaraFrameworkSelf-hosted, open-source AI agent operating system with multi-agent orchestration and MCP.Open sourceCosts not checkedTypeScript · recorded license: MITRecord checked · Recent push 31GitHub starsTwitterAPI.io MCP ServermcpGive MCP clients read-only tools for Twitter/X search and public account data.Open sourcePaid productTypeScript · recorded license: MITRecord checked · Recent push 1GitHub stars
Frequently asked
- What are the best TypeScript AI agents?
- By recorded GitHub star count, firecrawl, gemini-cli and MCP Reference Servers lead the TypeScript AI agents in this index of 111. The full list is below; star count does not prove suitability or continued maintenance. Sponsorship does not affect its order.
- Are these TypeScript AI agents open source and free?
- These records have recognized open-source software licenses recorded and are written primarily in TypeScript in this index. MIT is the most common licence here, on 70 of 111, across 7 licences in total. Check each license and deployment requirements. Hosting, model, API, and managed-service costs may apply.
- Why choose TypeScript AI agents specifically?
- Staying in your team's primary language — TypeScript — can help your team inspect and modify code it understands. Repository language does not establish supported user languages, SDKs or an offline deployment. 88 of these 111 have a recorded push within 90 days. A quiet repository alone does not establish whether the project is complete, supported or abandoned.