engram-tools
v0.3.7
Published
Shared memory for AI coding agents. Store, recall, and learn across tools, sessions, and teams.
Downloads
975
Maintainers
Readme
Engram Tools
Shared memory for AI coding agents. Engram lets MCP-compatible agents store what they learn, recall team knowledge, transfer lessons across repos, and report whether recalled memories actually helped.
What Works Today
- MCP server package:
engram-tools - HTTP API for hosted or custom agent integrations
- Persistent memories by workspace and repo
engram_startfor one-call session setup + smart context loadingengram_smarterfor task-specific context loading when switching tasksengram_store,engram_recall,engram_report_outcome,engram_get_context,engram_skill, andengram_setup- Outcome-based confidence updates
- Plan limits and daily API usage metering
- Stripe checkout/webhook plan updates
- Basic team dashboard for usage, limits, and recent memories
- PostgreSQL + pgvector semantic search when
VOYAGE_API_KEYis configured - Text-search fallback when embeddings are unavailable
Quick Start
npx engram-tools --setup engram_your_api_keyThe setup command writes MCP config for Claude Code, Cursor, Gemini CLI, Codex, OpenCode, and VS Code/Copilot project config when possible. For Claude Code, it also writes optional slash-command aliases for convenience.
After setup, restart your AI tool or start a new session. Most MCP clients load servers only at session startup. Start every client the same way: call engram_start once with project, repo, stack, role, market, and task.
If the conversation was compacted, summarized, resumed, or the agent feels prior context is incomplete, call engram_start again before continuing. If the agent is mid-session and only needs focused recovery, call engram_smarter with the current task context.
Manual MCP config:
{
"mcpServers": {
"engram": {
"command": "npx",
"args": ["-y", "engram-tools"],
"env": {
"ENGRAM_API_KEY": "engram_your_api_key",
"ENGRAM_API_URL": "https://api.engram.tools"
}
}
}
}Core Tools
engram_start
Start or recover a session in one call. This loads setup guidance, the Engram operating contract, and the most relevant memories/skill guides. Use it at the beginning of a session, after compaction/resume, when entering a repo, or when task context changes.
{
"project": "HouseCompass",
"repo": "housecompass.uk",
"role": "frontend product engineer",
"market": "UK property",
"task": "build the listing detail page",
"stack": ["Next.js", "TypeScript", "PostgreSQL"]
}engram_smarter
Load task-specific memories and matching skill guides in one call. Use this after engram_start, when switching tasks, or when recovering focused context mid-session.
{
"context": "Next.js 16 + Prisma signup bug, fixing API key setup",
"repo": "engram",
"include_skills": true
}engram_cross_pollinate
Find reusable lessons from other repos in the same workspace.
{
"target_repo": "engram",
"context": "Stripe webhook tier updates and signup reliability"
}engram_store
Save a convention, pattern, gotcha, solution, architecture note, or dependency quirk.
engram_recall
Search memories by semantic query, repo, type, or tags.
engram_report_outcome
Report whether a recalled memory helped. This updates confidence and improves future ranking.
HTTP API
Hosted API base:
https://api.engram.toolsUseful endpoints:
POST /api/v1/startPOST /api/v1/smarterPOST /api/v1/cross-pollinatePOST /api/v1/storePOST /api/v1/recallPOST /api/v1/reportPOST /api/v1/contextPOST /api/v1/skillPOST /api/v1/setupGET /api/v1/capabilities
All private endpoints require:
Authorization: Bearer <ENGRAM_API_KEY>Local Development
npm install
npm run db:setup
npm run dev:httpEnvironment:
DATABASE_URL=postgresql://...
ENGRAM_API_KEY=engram-dev-key-001
VOYAGE_API_KEY=optionalRun verification:
npm run typecheck
npm run build
npm run test:productThe product smoke test stores memories, calls /api/v1/smarter, and verifies /api/v1/cross-pollinate.
Status
Engram is in beta. The core memory, smarter context, cross-repo transfer, outcome-learning, hosted limits, API metering, Stripe plan updates, and basic dashboard flows are implemented. Scale-plan items such as SSO/SAML, self-hosted packaging, and SLA terms are handled as custom rollout work.
License
MIT
