Hi HN,
I built engrim to establish a local-first, open standard for cross-model AI agent memory.
As context windows scale past 1M+ tokens, developers face rapid attention dilution: reasoning degrades, and token costs multiply exponentially with every turn. But if you clear your agent's session (/clear) to save money and speed things up, the agent suffers total episodic amnesia, forgetting architectural rules, past debugging steps, and micro-decisions.
Engrim replaces attention dilution with a 4,000-character curated episodic working memory pack. It decouples your project's intelligence from single-vendor proprietary cloud silos. You can switch seamlessly from Gemini in Google Antigravity to Claude 3.7 in Claude Code to GPT-4o in Cursor or Windsurf mid-project—your agents pick up exactly where the others left off.
A few architectural details: - Under the hood, it's a zero-latency hybrid retrieval engine combining SQLite FTS5 (BM25 keyword search) with static vector embeddings (model2vec) using Reciprocal Rank Fusion (RRF). - Memory retrieval is gated per prompt and filtered by a relevance floor, meaning only high-signal records enter your token window. - Provenance Tracking: It maps the origin of every memory entry via an `origin_agent` field (antigravity, claude-code, cursor, cli, user) across multi-agent setups. - 100% Local & Offline: Runs entirely out of a local SQLite database (~/.engrim/memory.db) with POSIX 0600 file permissions and zero cloud telemetry.
Empirical Proof: I production-tested this across 105 continuous sessions on a 50,000-line algorithmic trading system. Over 153,000 tokens of architecture and parameter-tuning logs were consolidated into an active memory pack under 1,000 tokens. That represents a 99%+ cut in reloaded context costs on session restarts with zero architectural regression.
Quickstart: It configures environment lifecycle hooks automatically (e.g., configures hooks.json for Antigravity, settings.json hooks and CLAUDE.md for Claude Code, and registers the stdio MCP server for Cursor and Windsurf):
pip install engrim engrim setup --all
I'm hoping this helps developers escape cloud lock-in and keep their data sovereign while putting an end to massive token bills. I'd love to hear your thoughts on the schema approach, the hybrid RRF engine, or how you handle episodic state across different AI tools!
I hope you don't mind me asking you some ELI5 questions because I'd like to understand how this fits in with everything else.
I generally discourage my agents from storing memories locally because they don't travel; I'd much rather have a small in-repo document—whether it's an architectural decision or TODO or session log entry or runbook or environmental quirk or something else—that the prompt/CLAUDE.md/whatever can guide agents to grep and sed. Then I can dispatch work to a local agent, or a local agent running in a sandbox, or an agent running in a provider's cloud environment, or a GitHub agentic workflow running a headless harness, etc. and they all have access to it. Another benefit is that memory updates get PRs and reviews like everything else.
So what am I missing by not using something like engrim or gbrain?
Permanent docs definitely belong in git. This is just the desk scratchpad for messy session context so you can /clear freely without cluttering commit history or burning tool calls on grep. Anti Gravity has a large enough context window that seems to be less needed than Claude Code but the real value now with engrim is if you are using multiple services, your project is relevant when switching services. This was born from my long haul Claude Code development sessions and morphed into its current state from swapping around CLI services on the same projects.
Ahh, interesting. I have an issue today where my GitHub agentic workflows keep blowing through the context window that my local models can support; it ends up spending most of its runtime compacting over and over again. I've done all the usual stuff to slim down the fixed context and prevent it from slurping up too many files but it's still a recurring issue. Now I'm wondering if I can put engrim in the gh-aw container (or in the DinD sidecar it uses on ARC) and teach the headless claude harness how to use it, possibly even: "keep persistent context in engrim and use `/clear` instead of `/compact`". I'll play around with it. Thank you!