TypeScript · open-source evidence
TypeScript repositories using AI coding agents.
Across 5,264 cataloged TypeScript repositories, qmmit considered 1,921,469 commits and detected 268,792 agent-attributed commits—a 14% aggregate floor for this catalog slice.
TypeScript AI coding agentsFixed-window commit evidence with repository-level denominators.
Repository evidence
TypeScript projects with the most detected agent commits.
Only observations with at least 100 considered commits appear here. This orders detected evidence; it does not score project quality.
CATALOG #43,101MEASURED
vellum-ai/vellum-assistant
An AI Assistant that’s easy to setup, does your work 24/7, knows your preferences and gets better over time.
- Detected AI share
- 76.3%
- agent commits
- 21,860
- Commits considered
- 28,662
- Detected AI share
- 35.1%
- agent commits
- 6,716
- Commits considered
- 19,133
- Detected AI share
- 34.1%
- agent commits
- 5,136
- Commits considered
- 15,045
CATALOG #27,021MEASURED
levy-street/world-of-claudecraft
Measured Git commit evidence for the levy-street/world-of-claudecraft repository.
- Detected AI share
- 29.5%
- agent commits
- 4,142
- Commits considered
- 14,033
- Detected AI share
- 58.3%
- agent commits
- 3,695
- Commits considered
- 6,340
- Detected AI share
- 23.2%
- agent commits
- 3,326
- Commits considered
- 14,360
CATALOG #28MEASURED
n8n-io/n8n
Fair-code workflow automation platform with native AI capabilities. Combine visual building with custom code, self-host or cloud, 400+ integrations.
- Detected AI share
- 40.2%
- agent commits
- 2,636
- Commits considered
- 6,557
- Detected AI share
- 35.9%
- agent commits
- 2,594
- Commits considered
- 7,233
CATALOG #12,393MEASURED
melgarafael/DeskcommCRM
Open-source AI sales OS — self-hosted CRM with native AI agents + WhatsApp (WAHA). Open alternative to Kommo, Octadesk & Intercom for any business that sells by chat. MCP-ready, multi-tenant, LGPD.
- Detected AI share
- 71.8%
- agent commits
- 2,476
- Commits considered
- 3,449
CATALOG #11,815MEASURED
Expensify/App
Welcome to New Expensify: a complete re-imagination of financial collaboration, centered around chat. Help us build the next generation of Expensify by sharing feedback and contributing to the code.
- Detected AI share
- 4.7%
- agent commits
- 2,382
- Commits considered
- 50,501
CATALOG #48,100MEASURED
Runfusion/Fusion
Your Software Factory - build faster and better with multi node agents that work 24/7
- Detected AI share
- 16.9%
- agent commits
- 2,298
- Commits considered
- 13,590
CATALOG #20,223MEASURED
Natively-AI-assistant/natively-cluely-ai-assistant
Natively — Free open-source AI meeting assistant, interview copilot, and note taker. The best alternative to Cluely, Otter, Granola, Final Round AI, Fireflies, and Interview Coder. Real-time transcription, AI meeting notes, lecture recording, local RAG, BYOK, and stealth mode. Runs locally. No subscriptions. No data breaches.
- Detected AI share
- 71.1%
- agent commits
- 2,080
- Commits considered
- 2,925
- Detected AI share
- 32.9%
- agent commits
- 2,007
- Commits considered
- 6,105
CATALOG #29,670MEASURED
eneskirca/nodeterm
Node-based terminal manager for AI coding agents — tmux-backed terminals and parallel agent sessions as draggable nodes on an infinite pan/zoom canvas. macOS, Linux, and a browser Server Edition.
- Detected AI share
- 76.4%
- agent commits
- 1,908
- Commits considered
- 2,498
CATALOG #43,407MEASURED
kizuna-ai-lab/sokuji
Real-time two-way speech translation for bilingual meetings — auto-detects the spoken language and translates both directions, cloud or fully offline on-device. Desktop (Windows · macOS · Linux) + browser extension (Chrome · Edge) for Zoom, Meet, Teams & any app.
- Detected AI share
- 70.8%
- agent commits
- 1,833
- Commits considered
- 2,589
CATALOG #27,370MEASURED
MCPJam/inspector
Testing and evaluation platform to chat, inspect, and debug MCP servers, MCP apps, and ChatGPT apps.
- Detected AI share
- 63.7%
- agent commits
- 1,825
- Commits considered
- 2,864
CATALOG #48,844MEASURED
reticlehq/reticle
AI agents can generate code, but still struggle to understand what they build. Reticle brings Jev-style machine-native runtime perception to web & desktop applications.
- Detected AI share
- 77.6%
- agent commits
- 1,753
- Commits considered
- 2,260
- Detected AI share
- 39%
- agent commits
- 1,738
- Commits considered
- 4,453
CATALOG #26,816MEASURED
usertour/usertour
Usertour is an open-source user onboarding platform. It allows you to create in-app product tours, checklists, and surveys in minutes—effortlessly and with full control.The open-source alternative to Userflow and Appcues
- Detected AI share
- 81.6%
- agent commits
- 1,671
- Commits considered
- 2,048
CATALOG #203MEASURED
lobehub/lobehub
🤯 LobeHub is your Chief Agent Operator, organizing your agents into 7×24 operations by hiring, scheduling, and reporting on your entire AI team.
- Detected AI share
- 34.3%
- agent commits
- 1,651
- Commits considered
- 4,812
- Detected AI share
- 28.2%
- agent commits
- 1,606
- Commits considered
- 5,685
CATALOG #33,237MEASURED
open-mercato/open-mercato
The AI-Engineering Foundation Framework for business apps: open-source TypeScript, with multi-tenancy, RBAC, events and domain modules already decided as conventions and specs, so Cursor, Claude Code and Codex build features instead of re-deciding architecture. Start with 80% done.
- Detected AI share
- 37.9%
- agent commits
- 1,582
- Commits considered
- 4,177
CATALOG #18,960MEASURED
off-grid-ai/OGAM
The Swiss Army Knife of Offline AI. Chat, see, speak, and generate images on your phone or Mac — GGUF LLMs, vision, Whisper speech-to-text, Stable Diffusion, tool calling, and local-network servers. Runs on your CPU, GPU, or NPU. No account, no API key, zero data leaves your device.
- Detected AI share
- 40.2%
- agent commits
- 1,575
- Commits considered
- 3,918
- Detected AI share
- 53.8%
- agent commits
- 1,559
- Commits considered
- 2,896
Use this ecosystem view carefully
GitHub language classification is a repository-level snapshot, while the detector reads commit metadata. The aggregate is descriptive of this catalog slice and is not the published benchmark.