Cross-Agent Memory Bridge — Your AI never forgets again
Why • Quick Start • Scenarios • Features • Compare • Full Setup Guide
Your AI assistant forgets everything when you start a new chat. You spend 10 minutes re-explaining your architecture. Again. And if you switch from Cursor to Claude Code? Everything is gone. Again.
| Without Memorix | With Memorix |
|---|---|
| Session 2: "What's our tech stack?" | Session 2: "I remember — Next.js with Prisma and tRPC. What should we build next?" |
| Switch IDE: All context lost | Switch IDE: Context follows you instantly |
| New team member's AI: Starts from zero | New team member's AI: Already knows the codebase |
| After 50 tool calls: Context explodes, restart needed | After restart: Picks up right where you left off |
| MCP configs: Copy-paste between 7 IDEs manually | MCP configs: One command syncs everything |
Memorix solves all of this. One MCP server. Seven agents. Zero context loss.
Add this to your agent's MCP config file, restart — done:
{
"mcpServers": {
"memorix": {
"command": "npx",
"args": ["-y", "memorix@latest", "serve"]
}
}
}
📖 Where is my config file? → Full setup guide for all 7 agents Windsurf • Cursor • Claude Code • Codex • VS Code Copilot • Antigravity • Kiro
That's it. No API keys. No cloud accounts. No dependencies. Just works.
Monday morning — You and Cursor discuss auth architecture:
You: "Let's use JWT with refresh tokens, 15-minute expiry"
→ Memorix auto-stores this as a 🟤 decision
Tuesday — New Cursor session:
You: "Add the login endpoint"
→ AI calls memorix_search("auth") → finds Monday's decision
→ "Got it, I'll implement JWT with 15-min refresh tokens as we decided"
→ Zero re-explaining!
You use Windsurf for backend, Claude Code for reviews:
Windsurf: You fix a tricky race condition in the payment module
→ Memorix stores it as a 🟡 problem-solution with the fix details
Claude Code: "Review the payment module"
→ AI calls memorix_search("payment") → finds the race condition fix
→ "I see there was a recent race condition fix. Let me verify it's correct..."
→ Knowledge transfers seamlessly between agents!
Week 1: You hit a painful Windows path separator bug
→ Memorix stores it as a 🔴 gotcha: "Use path.join(), never string concat"
Week 3: AI is about to write `baseDir + '/' + filename`
→ Session-start hook injected the gotcha into context
→ AI writes `path.join(baseDir, filename)` instead
→ Bug prevented before it happened!
You have 12 MCP servers configured in Cursor.
Now you want to try Kiro.
You: "Sync my workspace to Kiro"
→ memorix_workspace_sync scans Cursor's MCP configs
→ Generates Kiro-compatible .kiro/settings/mcp.json
→ Also syncs your rules, skills, and workflows
→ Kiro is ready in seconds, not hours!
After 2 weeks of development, you have 50+ observations:
- 8 gotchas about Windows path issues
- 5 decisions about the auth module
- 3 problem-solutions for database migrations
You: "Generate project skills"
→ memorix_skills clusters observations by entity
→ Auto-generates SKILL.md files:
- "auth-module-guide.md" — JWT setup, refresh flow, common pitfalls
- "database-migrations.md" — Prisma patterns, rollback strategies
→ Syncs skills to any agent: Cursor, Claude Code, Kiro...
→ New team members' AI instantly knows your project's patterns!
| What You Say | What Memorix Does |
|---|---|
| "Remember this architecture decision" | memorix_store — Classifies as 🟤 decision, extracts entities, creates graph relations |
| "What did we decide about auth?" | memorix_search → memorix_detail — 3-layer progressive disclosure, ~10x token savings |
| "What happened around that bug fix?" | memorix_timeline — Shows chronological context before/after |
| "Show me the knowledge graph" | memorix_dashboard — Opens interactive web UI with D3.js graph |
| "Which memories are getting stale?" | memorix_retention — Exponential decay scores, identifies archive candidates |
| What You Say | What Memorix Does |
|---|---|
| "Sync my MCP servers to Kiro" | memorix_workspace_sync — Migrates configs, merges (never overwrites) |
| "Check my agent rules" | memorix_rules_sync — Scans 7 agents, deduplicates, detects conflicts |
| "Generate rules for Cursor" | memorix_rules_sync — Cross-format conversion (.mdc ↔ CLAUDE.md ↔ .kiro/steering/) |
| "Generate project skills" | memorix_skills — Creates SKILL.md from observation patterns |
| "Inject the auth skill" | memorix_skills — Returns skill content directly into agent context |
| Tool | What It Does |
|---|---|
create_entities |
Build your project's knowledge graph |
create_relations |
Connect entities with typed edges (causes, fixes, depends_on) |
add_observations |
Attach observations to entities |
search_nodes / open_nodes |
Query the graph |
read_graph |
Export full graph for visualization |
Drop-in compatible with MCP Official Memory Server — same API, more features.
Every memory is classified for intelligent retrieval:
| Icon | Type | When To Use |
|---|---|---|
| 🎯 | session-request |
Original task/goal for this session |
| 🔴 | gotcha |
Critical pitfall — "Never do X because Y" |
| 🟡 | problem-solution |
Bug fix with root cause and solution |
| 🔵 | how-it-works |
Technical explanation of a system |
| 🟢 | what-changed |
Code/config change record |
| 🟣 | discovery |
New insight or finding |
| 🟠 | why-it-exists |
Rationale behind a design choice |
| 🟤 | decision |
Architecture/design decision |
| ⚖️ | trade-off |
Compromise with pros/cons |
Run memorix_dashboard to open a web UI at http://localhost:3210:
- Interactive Knowledge Graph — D3.js force-directed visualization of entities and relations
- Observation Browser — Filter by type, search with highlighting, expand/collapse details
- Retention Panel — See which memories are active, stale, or candidates for archival
- Project Switcher — View any project's data without switching IDEs
- Batch Cleanup — Auto-detect and bulk-delete low-quality observations
- Light/Dark Theme — Premium glassmorphism design, bilingual (EN/中文)
Memorix can automatically capture decisions, errors, and gotchas from your coding sessions:
memorix hooks install # One-command setup
- Implicit Memory — Detects patterns like "I decided to...", "The bug was caused by...", "Never use X"
- Session Start Injection — Loads recent high-value memories into agent context automatically
- Multi-Language — English + Chinese keyword matching
- Smart Filtering — 30s cooldown, skips trivial commands (ls, cat, pwd)
| Mem0 | mcp-memory-service | claude-mem | Memorix | |
|---|---|---|---|---|
| Agents supported | SDK-based | 13+ (MCP) | Claude Code only | 7 IDEs (MCP) |
| Cross-agent sync | No | No | No | Yes (configs, rules, skills, workflows) |
| Rules sync | No | No | No | Yes (7 formats) |
| Skills engine | No | No | No | Yes (auto-generated from memory) |
| Knowledge graph | No | Yes | No | Yes (MCP Official compatible) |
| Hybrid search | No | Yes | No | Yes (BM25 + vector) |
| Token-efficient | No | No | Yes (3-layer) | Yes (3-layer progressive disclosure) |
| Auto-memory hooks | No | No | Yes | Yes (multi-language) |
| Memory decay | No | Yes | No | Yes (exponential + immunity) |
| Visual dashboard | Cloud UI | Yes | No | Yes (web UI + D3.js graph) |
| Privacy | Cloud | Local | Local | 100% Local |
| Cost | Per-call API | $0 | $0 | $0 |
| Install | pip install |
pip install |
Built into Claude | npx memorix serve |
Memorix is the only tool that bridges memory AND workspace across agents.
Out of the box, Memorix uses BM25 full-text search (already great for code). Add semantic search with one command:
# Option A: Native speed (recommended)
npm install -g fastembed
# Option B: Universal compatibility
npm install -g @huggingface/transformers
With vector search, queries like "authentication" also match memories about "login flow" via semantic similarity. Both run 100% locally — zero API calls, zero cost.
- Auto-detected — Project identity from
git remoteURL, zero config needed - Per-project storage —
~/.memorix/data/<owner--repo>/per project - Scoped search — Defaults to current project;
scope: "global"to search all - Zero cross-contamination — Project A's decisions never leak into project B
git clone https://github.com/AVIDS2/memorix.git
cd memorix
npm install
npm run dev # tsup watch mode
npm test # vitest (422 tests)
npm run lint # TypeScript type check
npm run build # Production build
📚 Documentation: Architecture • API Reference • Modules • Design Decisions • Setup Guide • Known Issues
Memorix stands on the shoulders of these excellent projects:
- mcp-memory-service — Hybrid search, exponential decay, access tracking
- MemCP — MAGMA 4-graph, entity extraction, retention lifecycle
- claude-mem — 3-layer Progressive Disclosure
- Mem0 — Memory layer architecture patterns
Apache 2.0 — see LICENSE
Made with ❤️ by AVIDS2
If Memorix helps your workflow, consider giving it a ⭐ on GitHub!