| What it does | Local code intelligence that shows its evidence
| Explain it once. Every AI knows it.
|
|---|
| Stage | Not given
| Not given
|
|---|
| Founded | Not given
| Not given
|
|---|
| Based in | Not given
| DE
|
|---|
| Pricing model | Free
| Not given
|
|---|
| Pricing | Not given
| Free: €0, 1 project, 25 MB storage, 500 recalls/month. Solo: €19/month (€15/year), 3 projects, 200 MB storage. Team: €49/month (€39/year), 10 projects, 900 MB storage, up to 5 people. Business: €199/month (€159/year), 25 projects, 7 GB storage, up to 20 people, SSO included.
|
|---|
| Key features | - Supports 50 languages with 53 registry IDs
- 16 SQLite tables for symbols, source bounds, imports and relationships
- 16 MCP agent tools for code analysis
- AST-based code indexing
- Incremental re-indexing with automatic freshness tracking
- Call-graph analysis
- Respects .gitignore and .bbignore files
- Shows file, line and evidence for every answer
- Local storage with no cloud required
- Optional embedding provider integration for semantic search
| - Learns from git history and CI runs
- Works with Claude Code, Cursor, Copilot and Windsurf
- Automatic context matching across sessions
- Team experience sharing with names and roles
- Saves decisions with reasoning behind them
- One-command setup via npx
- Loads 27 core tools instead of 124 for more context space
- Extracts lessons from recent commits during setup
- API keys and passwords redacted before storage
|
|---|
| What makes it different | - Every answer includes file location, line number and the relationship walked to get there
- Fully local operation with no cloud requirements
- Open source under MIT license
- Free to use with no paid plans or cost
| - Only MCP server keeping project experience across all AI editors on every machine and for whole teams
- Automatically learns from git history and CI without manual documentation
- Data stored in Germany with GDPR compliance and DPA for companies
- Preserves lessons outside conversation summaries after /compact
- Ranked #1 on LoCoMo in OmniMemEval comparison with 90.71 points
|
|---|
| 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) | 1 ▼ −1 (down) since last check | 18 ● no change since last check |
| Trust Flow (Majestic) | 0 | 9 |
| Citation Flow (Majestic) | 0 | 28 |
| Referring domains (Majestic) | 0 | 117 |