{"name":"crm: Run an Agent-First CRM for AI Agents","description":"Comp AI CRM is a TypeScript CRM built around eve, Vercel's durable-agent framework. Its agent researches and updates records on its own schedule, with evidence-based safeguards and human review for uncertain facts.","github":"https://github.com/trycompai/crm","url":"https://osrepos.com/repo/trycompai-crm","source":"osrepos.com","sourceDescription":"This repository profile is provided by osrepos.com, an open source repository discovery platform.","repositoryProfile":"https://osrepos.com/repo/trycompai-crm","generatedFor":"open source discovery and AI-assisted research","markdown":"https://osrepos.com/repo/trycompai-crm.md","json":"https://osrepos.com/repo/trycompai-crm.json","topics":["typescript","ai-agents","self-hosted","web-app","crm","sales-automation","contact-enrichment"],"keywords":["typescript","ai-agents","self-hosted","web-app","crm","sales-automation","contact-enrichment"],"stars":null,"summary":"Comp AI CRM is a TypeScript CRM built around eve, Vercel's durable-agent framework. Its agent researches and updates records on its own schedule, with evidence-based safeguards and human review for uncertain facts.","content":"## Overview\n\nComp AI CRM is a TypeScript CRM built around eve, Vercel's filesystem-first framework for durable agents. It addresses the limits of CRMs that leave research and record-keeping to people: its agent works through a queue on its own schedule, researches contacts and companies, and records findings as evidence rather than guessed facts.\n\nIt is a self-hosted, single-tenant web application for teams that want an agent to maintain CRM records while keeping people involved when evidence is uncertain. The agent can run without external research API keys, and the project includes a web app, API, and separately deployed agent.\n\n## Key Features\n\n- Durable agent sessions and scheduled work, backed by a database queue with expiring leases.\n- Tools for searching CRM history, identifying contacts, researching people, enriching companies, recording facts, and scheduling follow-ups.\n- Evidence-based record updates: strong evidence can update records, while weaker findings become suggestions for human review.\n- An Agent tab on contact, company, and deal records for conversations, progress, and questions requiring a person's input.\n- Optional service connections with read-only or read-and-write access, reviewed tools, and per-agent grants.\n- Gmail and calendar integrations, with mailbox sync; Microsoft mail access is read-only and forward-only.\n- A sandbox for agent work with network egress denied and no database credentials passed to the shell.\n- A TypeScript monorepo using Next.js, NestJS, Prisma, and PostgreSQL, with Bun and Turborepo.\n\n## Use Cases\n\n- A sales team wants an agent to research contacts and keep records current, while escalating uncertain identity matches for review.\n- A small team wants follow-ups scheduled from CRM work queues instead of relying on a person to run recurring research manually.\n- An organization wants to connect mailboxes for CRM context but restrict Microsoft access to reading messages and importing only newly checked mail.\n- A self-hosting team wants a single-tenant CRM it can deploy and configure itself, including its identity provider and agent integrations.\n\n## Our Take\n\nThis is a promising, actively maintained early-stage CRM for teams willing to operate a multi-service deployment in exchange for an agent that works continuously and treats evidence cautiously.\n\n**Good fit if:**\n- You want an agent-first CRM rather than a conventional CRM with a chat feature, and value evidence-backed updates with human review for uncertain facts.\n- Your team can run the Next.js app, NestJS API, agent, and PostgreSQL, and configure sign-in and any optional integrations it needs.\n- You want a project with recent commits and frequent releases; it has six contributors, with no measured single-contributor concentration.\n\n**Look elsewhere if:**\n- You need a mature CRM with a longer operating history; this repository is classified as new, at less than six months old.\n- You need a multi-tenant product, since the project deliberately has no organizations and is single-tenant.\n- You need a ready-made hosted CRM or want to avoid configuring and operating its separate app, API, agent, and database.\n\n## Project Health\n\n| Signal | Value |\n|---|---|\n| Status | **New**: less than six months old |\n| Last commit | 2026-10-22 (20 days ago) |\n| Commits, last 90 days | 24 |\n| Releases, last 12 months | 23 (latest v1.16.0, 2026-10-22) |\n| Contributors | 6 (top contributor: 57% of commits) |\n| Issues closed, last 90 days | 18+ (typically closed in 40 days) |\n| Pull requests merged, last 90 days | 34 (typically merged in 0 days) |\n| Project age | 3 months |\n\nChecked on 2026-11-12 with the GitHub API.\n\n## Project Facts\n\n- Language: TypeScript\n- License: MIT\n- Stars: 11.9k\n- Forks: 1.8k\n- Website: https://trycrm.ai\n- Archived: no\n\n## What You Need\n\nDetected in the repository:\n\n- Node.js >=22 (from package.json)\n- A Compose file to run it with its related services\n- Automated checks on GitHub Actions\n\n## Getting Started\n\nThe local quick start uses Bun and Docker Compose:\n\n```sh\ngit clone https://github.com/trycompai/crm.git\ncd crm\ncp .env.example .env\nbun install\ndocker compose up -d\nbun run db:deploy\nbun run dev\n```\n\nSet the required authentication and sign-in values in `.env` first. See the [README](https://github.com/trycompai/crm#readme) for OAuth setup, configuration, and deployment details.\n\n## License in Plain Words\n\n**MIT** (permissive).\n\n- Commercial use: yes\n- Modify and redistribute: yes\n- You must keep: the copyright and license notice\n- Share your changes: no\n\nA summary, not legal advice: the LICENSE file is what applies.\n\n## Alternatives\n\n- [twenty](https://osrepos.com/repo/twentyhq-twenty): Twenty is a configurable CRM for technical teams, while Comp AI centers on scheduled AI research and evidence-based record updates.\n- [crm](https://osrepos.com/repo/frappe-crm): Frappe CRM focuses on conventional lead, deal, and interaction workflows with calling and messaging integrations, rather than autonomous record research.\n- [atomic-crm](https://osrepos.com/repo/marmelab-atomic-crm): Atomic CRM organizes contacts, follow-ups, notes, and deals with React and Supabase, without Comp AI's scheduled agent-driven enrichment.\n\n| Project | Language | License | Stars | Status |\n|---|---|---|---|---|\n| **crm** | TypeScript | MIT | 11.9k | New |\n| [twenty](https://osrepos.com/repo/twentyhq-twenty) | TypeScript | – | 60.3k | Active |\n| [crm](https://osrepos.com/repo/frappe-crm) | Vue | AGPL-3.0 | 3.7k | Active |\n| [atomic-crm](https://osrepos.com/repo/marmelab-atomic-crm) | TypeScript | MIT | 1.3k | Active |\n\n## Considerations\n\n- The project is young, so its recent activity and releases are encouraging but do not establish long-term operational maturity. It has handled at least 18 issue closures in the measured period, with a median close time of 40 days.\n- Local development requires Bun, Node.js 22 or newer, Docker Compose, and PostgreSQL. Production deployment involves three separate services plus a database.\n- Automated tests are not indicated in the supplied project requirements, so teams should assess their own verification needs before adopting it.\n- External research and integrations depend on configuration. The agent can work without optional research keys, but that limits its sources.\n- The project is single-tenant by design, which may not suit organizations that need separate customer workspaces.","metrics":{"detailViews":4,"githubClicks":3},"dates":{"published":null,"modified":"2026-11-12T05:08:34.000Z"}}