Open Source TypeScript Projects
TypeScript is a programming language that adds static types and related development features to JavaScript. Its type system can catch many mistakes before code runs, clarify how functions and data structures are meant to be used, and make large codebases easier to change. TypeScript code is typically compiled into JavaScript, so it can run in browsers, servers, and other JavaScript environments. It is used for applications of many sizes, from small scripts to shared libraries and complex web services.
Open source TypeScript tools include application frameworks, UI libraries, command-line utilities, testing tools, build systems, and type definitions. When choosing one, consider its license, release and maintenance history, documentation, compatibility with your runtime and existing stack, and any setup or infrastructure requirements. Also check how actively it is used and whether its conventions fit your team. These tools can help frontend and backend developers, maintainers of JavaScript projects, and teams building software that benefits from clearer interfaces and reliable refactoring.
374 repositories · updated October 17, 2026
agentrc: Prepare Repositories for AI Coding Agents
AgentRC assesses a repository’s readiness for AI coding agents, then generates tailored instructions and development configuration. It can also evaluate those instructions over time, making it useful for teams that want agent context grounded in their codebase.
ActiveHealth 69/100
SocratiCode: Give AI Agents Searchable Codebase Context
SocratiCode is a local-first MCP server and plugin that helps AI agents explore large codebases with semantic search, dependency graphs, and symbol-level impact analysis. It also indexes project context such as API specs and database schemas.
ActiveHealth 75/100
sandbox-runtime: Restrict Process Access Without Containers
Anthropic Sandbox Runtime wraps processes with OS-enforced filesystem and network restrictions, aimed especially at AI agents and MCP servers. It is actively maintained, but remains a beta research preview with platform-specific setup and limitations.
ActiveHealth 66/100
plur: Share Persistent Memory Across AI Agents
PLUR gives AI agents a shared, local-first memory store of readable YAML files. It suits developers who want corrections and project conventions to carry across sessions and tools without relying on a hosted memory service.
ActiveHealth 75/100
Codeoid: Coordinate AI Coding Agents Across Sessions
Codeoid runs multiple AI coding-agent sessions through one daemon, with shared memory and terminal, web, and Telegram clients. It suits developers coordinating long-running or parallel work who want session continuity across several agent backends.
ActiveHealth 61/100
nanoclaw: Run Secure AI Agents in Messaging Apps
NanoClaw runs AI assistants in isolated containers and connects them to messaging channels and scheduled tasks. It suits individuals who want a compact, customizable assistant they can inspect and adapt, with container-based boundaries around agent access.
ActiveHealth 68/100
meridian: Connect Coding Clients to Claude and Antigravity
Meridian is a local API bridge for using Claude and Antigravity subscriptions with coding clients such as Pi and OpenCode. It also provides usage monitoring and an optional Mac app, with Antigravity currently marked as a preview.
ActiveHealth 77/100
iPolloWork: Coordinate AI Agents and Edit Their Work
iPolloWork is a local-first desktop workbench for coordinating projects across Codex, DeepSeek Harness, and OpenCode. It brings agent tasks, extensions, and editable outputs for code and creative work into one workspace.
ActiveHealth 63/100
fallow: Analyze TypeScript and JavaScript Codebases
fallow builds a repository graph to find code health issues, complexity hotspots, duplication, architecture violations, styling drift, and unused code. Use it from the CLI, CI, editors, or coding agents, with findings scoped to changed files.
ActiveHealth 74/100
agent-worktrees: Manage Claude Agents Across Git Worktrees
A VS Code extension for starting and monitoring Claude Code agents in isolated Git worktrees. It brings agent status, worktree Git state, and optional GitHub pull request checks into one panel.
NewHealth 49/100
agentwatch: Monitor AI Agent Activity Locally
agentwatch combines logs from multiple coding agents into a local timeline with event details, cost tracking, alerts, and search. It suits developers who run several agents and want visibility without sending data to a cloud service.
QuietHealth 21/100
image-blaster: Turn Images into 3D Environments and Assets
image-blaster uses Claude skills and external generation services to turn an image into a 3D environment, object meshes, and sound effects. It is designed to quickly create starting points for game, 3D, and web projects.
QuietHealth 17/100