Blackman99/deskfolk
Blackman99/deskfolk has 46 GitHub stars and 7 forks. Star changes are not measured yet. Last checked 2026-11-09 20:09 UTC. Last push 2026-11-04.
Hand it off. Walk away. Return to results.
Measured star growth
- in 24h
- Update delayed
- in 7 days
- Update delayed
- in 15 days
- Update delayed
- in 1 month
- Update delayed
Net star changes over overlapping periods, not daily totals. Missing measurements are left blank. Stars measure attention, not software quality.
README.md
Original
Also in 中文
Deskfolk
Hand it off. Walk away. Return to results.
Files are kept by job and ticket, and played, read and annotated right in the app; every turn is on the flow, with the ticket it works on and why, and the task map plays back which folder it worked in, step by step; after a delivery, Bots look back and do better next time.
Multi-day, multi-step jobs that need rework are safe to hand off too: when a Bot says done, the app checks first.
No API key needed: pick the Claude Code, Codex, Grok, OpenCode, Antigravity or ZCode you have signed in on this computer, or any ACP agent, in the setup wizard, and Bots run on your own sign-in; in a project session you talk to Claude Code or Codex itself, in a folder of yours.
Or connect OpenAI, Anthropic, Xiaomi MiMo, Qwen, DeepSeek, OpenRouter or any OpenAI- or Anthropic-compatible address, or Ollama, LM Studio and llama.cpp on your machine.
Website · Download · About and install · 简体中文

It asks you first, as much as its permission mode says

Say stop and it stops; your next line sets it going

Done has a definition: checks, a review, your OK

Come back to results: the chat, the work and the board together

Where the work went: the job as a town of its folders, played back step by step

Project sessions: Claude Code or Codex in a folder of yours, in the same window as your Bots

On your phone too: the conversations, the answer, the job's checks, the film
About and install · Roadmap · Development · Contributing · Security · MIT
Explore related projects
affaan-m/ECC
The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.
300,954 starsNousResearch/hermes-agent
The agent that grows with you
262,546 starsmultica-ai/andrej-karpathy-skills
A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls.
231,992 starsfirecrawl/firecrawl
Supercharge your AI agents with data from the web and beyond. Building the library for superintelligence. 🔥
200,444 stars