trycompai/crm
- Source
- GitHub
- First trending
- Category
- Agents
- GitHub stars
- 10,540
- Main language
- TypeScript
This page introduces an external open-source repository. It is not an HDATF product.

What it does
Comp AI CRM is an open-source CRM run by an agent that works through its own queue and schedule. Its tools report observed evidence; strong evidence is written to records, and weak evidence becomes a suggestion for a person.
How it helps ATF
Its rule of writing only strong evidence to records and leaving weak evidence for a person to settle is worth comparing with how Harness checks results with evidence. Its agent that keeps working through its own queue could also be a reference.
License
MIT Permissive. Commercial use and changes are allowed if the copyright notice is kept.
More in this category
- holaboss-ai/holaOS
holaOS is a local-first agentic workspace where apps open beside an agent that can drive them. It connects existing systems, chat tools, a browser and local files with shared memory, and works with agents such as Claude Code or Codex. - cloudflare/computer
A preview TypeScript package that gives agents a virtual filesystem stored in SQLite inside a Durable Object, with pluggable execution backends: a sandbox container with a FUSE mount, a shell in a Dynamic Worker, or JavaScript modules. - anywhere-labs/dsh-desktop
A community-built Windows and macOS desktop client for DeepSeek Harness, not affiliated with DeepSeek. It runs a pinned upstream version unchanged and adds a window, tray, terminal, updates and settings, combined through the plugin system. - huangruiteng/loopx
LoopX is a local-first control plane that runs on top of agent harnesses such as Codex, Claude Code and Cursor. It keeps objectives, gates, todos, evidence, quota and handoffs across turns, while the harness executes bounded work. - awesome-dsh-plugin/awesome-dsh-plugin
A curated list of plugins for DeepSeek Harness, also called dsh.
Only repositories in the ranked Trendshift lists are included, and the lists are used only to find candidates. We do not copy their ranks. Descriptions, licenses and star counts come from each GitHub repository. The notes are our own reading. We have not tested these projects, and a place on a trending list does not prove quality.