awesome-repositories.com
Blog
MCP
awesome-repositories.com

Discover the best open-source repositories with AI-powered search.

ExploreCurated searchesOpen-source alternativesSelf-hosted softwareBlogSitemap
ProjectMCP serverAboutHow we rankPress
LegalPrivacyTerms
© 2026 Bringes Technology SRL·VAT RO45896025·hello@awesome-repositories.com
trycompai avatar

trycompai/crm

0
View on GitHub↗
trycrm.ai↗

Crm

This is an open-source, self-hosted customer relationship manager built around autonomous AI agents. A durable background agent with its own work queue researches contacts, companies and deals, decides what to examine next, schedules follow-up rechecks with a stated reason shown to the sales rep, and stays within a research budget while no one is present. Each contact, company and deal also has a chat tab where you can talk to the agent, see its steps, discarded leads and questions, and keep the conversation across page reloads.

What sets it apart is how it treats what the agent finds. Facts about a person are written to the record only when observed evidence, scored by a ledger, supports them; weaker findings go to a human as suggestions. Agents run shell commands in a sandbox with no network access and no database credentials, so customer email content cannot leak out through a shell. Outside services are connected by an owner or admin with read-only or read-and-write access, and each deployed agent gets a narrower, reviewed set of tools than the connection allows. Disconnecting a service blocks its calls immediately.

Around the agent, the CRM enriches records from a web domain, a profile link, stored email threads, meetings and signature blocks, with optional cited web search. Enrichment fills in company logos, colours and industry, and a person's current title, employer and past roles. Email and calendar data is imported through read-only access and refreshed on a recurring schedule without touching older messages. List filters, sort order and page number are kept in the address bar, so a copied link shows another user the same view.

The stack deploys as three separate services (app, API and agent) against a single Postgres database, configured through one environment file with optional extras. Team sign-in uses Google, Microsoft or a custom identity provider, limited to approved email domains or individual addresses.

AI search

Explore more awesome repositories

Describe what you need in plain English — the AI ranks thousands of curated open-source projects by relevance.

Start searching with AI

Features

  • Autonomous Research Agents - Runs a durable background agent with its own work queue that researches contacts and deals, picks what to examine next, and stays within a budget.
  • Customer Relationship Management Systems - A customer relationship management system built around autonomous AI agents that research, enrich and track contacts, companies and deals, with persistent per-record agent conversations.
  • Evidence-Backed Deliverable Drafting - Writes facts about a person to the record only when ledger-scored evidence supports them, sending weaker findings to a human as suggestions.
  • Evidence-Gated Claim Ledgers - Scores each discovered fact against observed evidence in a ledger, writing strong results to the record and routing weak ones to a human.
  • Evidence-Gated Fact Recording - Writes facts to the record only when a ledger of observed evidence supports them, routing weaker findings to a human as suggestions.
  • Contact and Company Records - Fills in company logos, colours, industry and a person's title, employer and past roles from a domain, profile link, emails and meetings.
  • Record Enrichment - Fills in company logos, colours, industry and a person's title, employer and past roles from a domain or profile link.
  • AI-Powered Agents - Runs an autonomous agent that researches contacts and companies, schedules follow-up rechecks, and brings findings back for a sales rep to review.
  • Customer Relationship Management - Provides a customer relationship manager you run on your own infrastructure, with team sign-in limited to approved email domains or addresses.
  • MCP Tool Allow Lists - Gives each deployed agent a narrower, reviewed set of tools than its connection allows, and blocks calls immediately on disconnect.
  • Agent Governance - Controls which outside services agents may use through owner-approved connections, reviewed tool lists and a sandbox that keeps customer data from leaking.
  • Per-Record Agent Chats - Adds a chat tab to each contact, company and deal showing the agent's steps, discarded leads and questions, persisted across reloads.
  • Open Source CRM Platforms - Released as open source and self-hosted, deploying app, API and agent as separate services against a single Postgres database.
  • Agent Command Sandboxing - Runs agent shell commands in a sandbox with no network access and no database credentials, so customer email content cannot leak.
  • External Service Connection Management - Lets owners or admins connect outside services with read-only or read-write access, with discovered tools reviewed before agents may use them.
  • CRM Deployments - Deploys the app, API and agent as separate services against one Postgres database, configured through a single environment file.
  • Email and Calendar Integrations - Imports mail threads and calendar events from connected accounts using read-only access and refreshes them on a recurring schedule without touching older messages.
  • Agent Queue Polling - Background agent claims tasks from a leased queue so parallel workers each take separate items, with follow-ups scheduled for later.
  • Agent Tool Permissions - Gives each deployed agent a narrower reviewed set of tools than its service connection allows, and blocks all calls the moment a service is disconnected.
11,892 stars·1,767 forks·TypeScript·MIT·0 views

Star history

Star history chart for trycompai/crmStar history chart for trycompai/crm

How this analysis was created: This summary and feature list are AI-generated from collected project material and can contain mistakes. Stars, license and language are imported from GitHub. Inclusion does not mean that we have tested or audited this project. Check the source documentation for any feature you depend on. Learn more on our About page.

Frequently asked questions

What does trycompai/crm do?

This is an open-source, self-hosted customer relationship manager built around autonomous AI agents. A durable background agent with its own work queue researches contacts, companies and deals, decides what to examine next, schedules follow-up rechecks with a stated reason shown to the sales rep, and stays within a research budget while no one is present. Each contact, company and deal also has a chat tab where you can talk to the agent, see its steps, discarded leads and…

What are the main features of trycompai/crm?

The main features of trycompai/crm are: Autonomous Research Agents, Customer Relationship Management Systems, Evidence-Backed Deliverable Drafting, Evidence-Gated Claim Ledgers, Evidence-Gated Fact Recording, Contact and Company Records, Record Enrichment, AI-Powered Agents.

Which projects share features with trycompai/crm?

Projects with overlapping indexed features include: macro-inc/macro — Macro is a unified team workspace that brings email, chat, documents, tasks, calls, and customer records into one… copilotkit/openbot — OpenBot is a self-hosted workspace where teams run AI bots as coworkers. Each bot gets its own isolated computer with… twentyhq/twenty — Twenty is a headless customer relationship management framework that enables developers to build, version, and deploy… pewdiepie-archdaemon/odysseus — Odysseus is a self-hosted AI workspace and autonomous agent framework designed for deploying and managing large… builderz-labs/mission-control — Mission Control is a self-hosted web dashboard that acts as a control plane for autonomous AI coding agents. It lets… thunderbird/thunderbolt — Thunderbolt is an open-source, self-hostable AI chat client that runs on web, desktop (macOS, Linux, Windows) and…

Projects sharing features with Crm

These projects share indexed features with Crm. Shared tags can include platform or build tooling; verify the primary use case before treating a result as a replacement.
  • macro-inc/macromacro-inc avatar

    macro-inc/macro

    6,195View on GitHub↗

    Macro is a unified team workspace that brings email, chat, documents, tasks, calls, and customer records into one place. Items are connected by mentions that create two-way links, so any email, document, task, or contact can be traced back to the conversations and work tied to it. Autonomous AI agents run inside the workspace and draw on a shared team memory that is refreshed each night from email, messages, tasks, documents, and calls. Agents can be started by assigning them work through direct messages, mentions, or routines, or automatically when configured triggers fire. They run in sandb

    Rustagentaiai-agents
    View on GitHub↗6,195
  • copilotkit/openbotCopilotKit avatar

    CopilotKit/OpenBot

    10,393View on GitHub↗

    OpenBot is a self-hosted workspace where teams run AI bots as coworkers. Each bot gets its own isolated computer with a browser, workspace files and tools. Agents from any framework can be connected over the AG-UI protocol, and built-in bots can run alongside them. People converse with bots one-to-one or in groups, watch the bot's screen and the commands it runs, and can take over the browser when an agent hits a login wall or a two-factor prompt. Governance is central to the project. Every browser, file and tool action passes through a policy gateway that checks permissions and writes an aud

    TypeScriptag-uiagent-governanceai-agents
    View on GitHub↗10,393
  • twentyhq/twentytwentyhq avatar

    twentyhq/twenty

    60,609View on GitHub↗

    Twenty is a headless customer relationship management framework that enables developers to build, version, and deploy custom business applications using code. By utilizing a declarative approach to data modeling, the platform allows for the definition of custom objects, fields, and complex relationships directly within the source code. This schema-driven architecture automatically generates corresponding REST and GraphQL APIs, ensuring that data structures and interface components remain synchronized across development and production environments. The platform distinguishes itself through a m

    TypeScriptcrmcrm-systemcustomer
    View on GitHub↗60,609
  • pewdiepie-archdaemon/odysseuspewdiepie-archdaemon avatar

    pewdiepie-archdaemon/odysseus

    95,388View on GitHub↗

    Odysseus is a self-hosted AI workspace and autonomous agent framework designed for deploying and managing large language models. It serves as a centralized platform for orchestrating agentic tasks, utilizing a model context protocol server to connect AI models to external system utilities, browser automation, and local hardware. The system distinguishes itself through a combination of retrieval-augmented generation and a RAG knowledge base, using vector stores and local embeddings to provide persistent semantic memory. It further integrates AI-driven communication management to triage email i

    Python
    View on GitHub↗95,388
Compare all 30 related projects→