piia-engram
Enables persistent, portable context across multiple AI tools without vendor lock-in or cloud storage risks, reducing friction when switching between Claude,…
Local-first 'AI work identity' layer served over MCP: your preferences, quality bar, lessons learned, and project context live as JSON/Markdown files under ~/.engram/, and MCP-compatible tools — Claude Code, Codex, Cursor, Claude Desktop — read from the same store. A setup wizard auto-detects installed AI tools and writes their MCP config after confirmation. High-risk memory writes (credentials, shell commands) wait for user review; no cloud account required.
- Ask Claude to remember your project context and coding preferences across multiple conversations automatically.
- Generate consistent code style suggestions by storing your team's architectural decisions in one place.
- Find previously discussed solutions to recurring problems without re-explaining your codebase each time.
Enables persistent, portable context across multiple AI tools without vendor lock-in or cloud storage risks, reducing friction when switching between Claude, other LLMs, or specialized agents.
Engineering teams integrating multiple AI tools into workflows who need consistent session state without external dependencies.
https://github.com/Patdolitse/piia-engram
By Patdolitse
How to Get It
pip install piia-engram && engram setup
Tip: Paste this into a Claude Code conversation. Verify command matches your Claude Code version.
After installing, paste this into Claude:
Remember my project context and coding preferences across multiple conversations automatically
Trust Signals Auto-scanned
Community Pulse New
No community discussions found yet. This doesn't mean the tool isn't good — it may be new or serve a niche use case.
Reviewer notes
Auto-scanned review. These are observations, not a security certification.
Scored from trust signals (evidence-eval-v1): 162 GitHub stars; contributors unknown; last commit 0d ago; license Apache-2.0.
Things to check
- AGPL v3 license (copyleft) — check compliance before commercial embedding. Low/medium-risk memory writes are auto-absorbed by default (auditable and reversible); set ENGRAM_APPROVAL=strict to gate every write. Cross-tool continuity is proven for Claude Code -> Codex; several other clients are listed as 'expected to work' rather than verified.
- License (AGPL-3.0) may restrict commercial use. Check with your legal team.
- Single maintainer. Consider the risk if this person stops maintaining the project.
How to evaluate tools before deploying →
Data shown here comes from public APIs and automated scanning. Reviewer notes reflect one person's experience. This is not a security certification or legal recommendation. Always evaluate tools according to your own organization's policies.
Evaluation
Scored from trust signals (evidence-eval-v1): 162 GitHub stars; contributors unknown; last commit 0d ago; license Apache-2.0.