| What it does | Open-source memory platform for AI agents
| Infrastructure layer connecting agents to the open-source ecosystem
|
|---|
| Stage | Not given
| Not given
|
|---|
| Founded | Not given
| Not given
|
|---|
| Based in | DE
| US
|
|---|
| Pricing model | Not given
| Free
|
|---|
| Pricing | Free: $0/month with 1M tokens and 1 workspace (no card required). Standard: $1.00 per 1M tokens plus $5 per additional workspace. Enterprise: contact for pricing with bring-your-own-cloud deployment. Open-source engine available free to self-host.
| Not given
|
|---|
| Key features | - Unified vector search, knowledge graphs, and relational storage
- Automatic knowledge graph generation from data sources
- Multi-tenant support with isolated workspaces
- Data source integrations (Slack, Notion, Google Drive, GitHub, etc.)
- Self-improving memory that learns from use
- Multiple deployment options (cloud, self-hosted, air-gapped)
- Agent framework integrations (LangGraph, CrewAI, OpenAI SDK, MCP)
- Support for multiple vector and graph databases
- GDPR compliance and encryption at rest and in transit
- Built-in graph visualization of company brain
| - Search code by keywords, API names, or quoted phrases across packages and repositories
- Read versioned source code at specific versions or git refs with symbol selectors
- Compare source changes between package versions or repository refs
- Check package health, adoption, license, downloads, and open advisories
- Inspect direct and transitive dependencies with resolved versions
- Check security vulnerabilities and affected versions for packages
- Generate code examples grounded in open-source projects with cited sources
- Ask research questions about packages with cited sources and read commands
- Browse documentation pages and search by keywords with exact page locations
- Review upgrade impacts including vulnerabilities, changelog, and dependency changes
|
|---|
| What makes it different | - Combines vectors with graph relationships and generated data models for connected context retrieval
- State of the art performance on BEAM benchmark (79% vs 73.4% at 100k tokens)
- Keeps memory costs flat as data grows compared to baseline LLM approaches
- Fully open-source with no database lock-in
- Updates memory as source data changes, not just static snapshots
| - Version-aware indexing ensures agents get code and documentation matching their exact dependency versions, not latest releases
- Integrated index of code, documentation, packages, and dependency graphs in one interface through MCP, CLI, and API
- Deterministic results with exact file locations, line ranges, and symbol definitions for reliable agent decisions
- Supports open-source repositories not published as packages plus major package registries like npm, PyPI, and crates.io
|
|---|
| Free plan | Not given
| Not given
|
|---|
| Open source | Not given
| Not given
|
|---|
| Platforms | Not given
| Not given
|
|---|
| Public API | Not given
| Not given
|
|---|
| Community votes | 0 | 0 |
|---|
| DR (Domain Rating by Ahrefs) | 70 ● no change since last check | 52 ● no change since last check |
|---|
| Trust Flow (Majestic) | 14 | 7 |
|---|
| Citation Flow (Majestic) | 43 | 34 |
|---|
| Referring domains (Majestic) | 1089 | 247 |
|---|
GitHits