Show HN: Engrim – A universal, local-first SQLite memory engine for AI CLIs

Engrim, a universal local-first SQLite memory engine for AI CLIs, has been released on Hacker News, claiming to preserve project decisions and state across model switches with a 99%+ reduction in reloaded context cost. The tool, tested across 105 continuous sessions on a 50,000-line algorithmic trading system with zero regressions, integrates with Google Antigravity, Claude Code, Cursor MCP, and Windsurf, and is installable via pip.

The Universal Cross-Model & Cross-Agent Episodic Memory Store. A local-first, project-scoped SQLite memory engine that allows developers to freely switch between models and environments Google Antigravity , Claude Code , Cursor MCP , Windsurf on the SAME project without losing architectural decisions, user constraints, or project state. "Why pay for 200,000 tokens of forgotten noise on every turn? The models are disposable utilities; your project's decisions are not." As context windows scale to 1M+ tokens, developers face attention dilution : reasoning degrades, cost multiplies with every conversational turn, and clearing context causes total amnesia. engrim replaces attention dilution with 4,000 characters of curated episodic working memory : - Switzerland of AI Memory : Decouples project intelligence from any single AI vendor or proprietary cloud silo. Switch from Gemini 3.8 in Antigravity to Claude 3.7 Sonnet in Claude Code to GPT-4o in Cursor mid-project — your agents pick up right where the others left off. - Save Button for Autonomous Coding : Externalize decisions, constraints, and state as you work. Clear your agent session freely /clear and watch context reload intact. - Smart, Hot Context Loading : Combines SQLite FTS5 bm25 keyword search with static vector embeddings model2vec in a zero-latency hybrid reciprocal-rank fusion engine. Tested across 105 continuous sessions on a 50,000-line algorithmic trading system. Zero regressions across 186 unit tests, zero context amnesia across model switches. In production testing on an active algorithmic trading codebase running real capital: - Over 153,000 tokens of work across days of architecture, parameter tuning, and debugging was consolidated into an active memory pack under 1,000 tokens <1% of the context window . - That is a 99%+ cut in reloaded context cost on every session restart. - Seamlessly switched between Google Antigravity CLI, Claude Code, and Cursor MCP on identical repos with zero model drift or architectural regression. graph TD subgraph Agents "Supported Agent Environments" AGY "Google Antigravity<br/ PreInvocation & Stop Hooks " CLAUDE "Claude Code<br/ SessionStart & Stop Hooks " CURSOR "Cursor / Windsurf<br/ Model Context Protocol stdio " end subgraph CoreEngine "engrim Core Engine v1.3.0 " ADAPTERS "Adapters & Hooks<br/ agy, claude, mcp " PROVENANCE "Agent Provenance Engine<br/ origin agent tracking " ROUTER "Hybrid Retrieval & Minder<br/ bm25 lexical + vector cosine " end subgraph Storage "Local-First SQLite Store ~/.engrim/memory.db " MEMORIES "Curated Memories<br/ decisions, facts, feedback " FTS5 "FTS5 Full-Text Search<br/ porter stemmer, triggers " VEC "Vector Embeddings<br/ model2vec static embeddings " LOG "Flight Recorder Log<br/ turns + action lines " end AGY <-- |"hook / CLI"| ADAPTERS CLAUDE <-- |"hook / CLI"| ADAPTERS CURSOR <-- |"JSON-RPC stdio "| ADAPTERS ADAPTERS -- PROVENANCE PROVENANCE -- ROUTER ROUTER -- MEMORIES MEMORIES --- FTS5 MEMORIES --- VEC ADAPTERS -- LOG pip install engrim Run engrim setup without arguments. It automatically detects installed environments on your machine and configures them all: engrim setup - If ~/.gemini exists$\rightarrow$ wires Antigravity lifecycle hooks, skill, and MCP server. - If ~/.claude exists$\rightarrow$ wires Claude Code SessionStart, Stop, status line, and CLAUDE.md. - If ~/.cursor exists$\rightarrow$ generates and merges Cursor MCP configuration. engrim setup --agy - Configures ~/.gemini/config/hooks.json to execute engrim hook --agent agy --event boot on PreInvocation and engrim hook --agent agy --event stop on Stop . - Deploys the canonical Antigravity skill to ~/.gemini/config/skills/engrim/SKILL.md . - Registers the MCP server in ~/.gemini/antigravity-cli/mcp config.json and ~/.gemini/config/mcp config.json . engrim setup --claude - Wires SessionStart , SessionEnd , Stop , and UserPromptSubmit hooks in ~/.claude/settings.json . - Configures live ambient status line in Claude Code's status bar. - Appends memory usage notes to ~/.claude/CLAUDE.md . engrim setup --cursor - Adds engrim to ~/.cursor/mcp.json running engrim serve --mcp . Add engrim to your ~/.codeium/windsurf/mcp config.json : { "mcpServers": { "engrim": { "command": "engrim", "args": "serve", "--mcp" } } } engrim setup --all - Configures every supported environment in one command. Use --dry-run with any setup command to inspect changes without modifying disk . When multiple agents collaborate on a single codebase, provenance matters. engrim records the origin of every memory entry with the origin agent field: - Allowed values: antigravity , claude-code , cursor , cli , or user . - Automatically populated based on the active hook, MCP client, or CLI session. - Subtly surfaced in engrim context and engrim list : 🧠 engrim · memory restored for this project — you don't have to re-explain · /workspace 18 of 54 curated records loaded ~3850 chars · the rest one recall away DECISION - 961 DECISION via Antigravity : Inverted stop loss matrix for high volatility risk, execution - 942 DECISION via Claude Code : Switched primary database from MongoDB to PostgreSQL db, schema - 910 DECISION via Cursor : Standardized on Pydantic v2 schemas across API boundaries api, types Existing databases are non-destructively migrated on first access via ALTER TABLE memories ADD COLUMN origin agent TEXT . Launch the zero-dependency, JSON-RPC 2.0 stdio MCP server: engrim serve --mcp or: engrim mcp stdout is strictly reserved for JSON-RPC messages, redirecting all diagnostic logs to stderr . | Tool | Signature | Purpose | |---|---|---| | engrim recall | query: str, project: str = "auto", k: int = 5, type: str = None | Hybrid keyword + semantic search over project memory. | | engrim add | type: str, summary: str, detail: str = None, tags: list str = | Write a durable memory record persisted across sessions. | | engrim context | project: str = "auto", budget: int = 4000 | Retrieve the session-boot memory pack within a character budget. | | engrim review | project: str = "auto" | Check uncaptured decisions from transcript logs before clearing. | | Command | Usage | Description | |---|---|---| | engrim add | engrim add -t decision -s "..." --origin-agent agy | Insert memory record types: decision , fact , feedback , state , user , reference . | | engrim recall | engrim recall -q "database" | Ranked hybrid recall for the project --log searches raw turns . | | engrim context | engrim context -b 4000 | Priority-ordered, budget-capped session-boot pack. | | engrim hook | engrim hook --agent agy --event boot | Agent lifecycle hook runner for Antigravity and Claude Code. | | engrim setup | engrim setup --agy\|--claude\|--cursor\|--all | Universal multi-agent environment configuration. | | engrim serve | engrim serve --mcp | Start stdio MCP server for agent integrations. | | engrim review | engrim review | "Safe to clear" coverage check: scans logs for uncurated decisions. | | engrim list | engrim list -k 20 | List recent memories for the current project. | | engrim supersede | engrim supersede --id 12 --status superseded | Mark a record superseded without erasing history. | | engrim sync | engrim sync DIR | Mirror markdown memories into the store idempotent seed-once . | 1. Capture as you work : Whenever a major decision or architectural rule is made, run engrim add or invoke engrim add via your agent. 2. Use resume-pointer : Before ending a session or clearing, add a record tagged resume-pointer describing the immediate next task. The newest pointer is pinned under ▶ RESUME HERE at the top of the next session's boot pack. 3. Verify with engrim review : Check that all recent decisions are captured. 4. Clear freely /clear : The session window is wiped clean; engrim automatically re-injects the active memory pack on the next prompt or invocation. - 100% Local & Offline : All memory records and logs reside in a local SQLite file ~/.engrim/memory.db . No telemetry, no cloud sync, no tracking. - Model Storage : Uses model2vec for local static embeddings ~30ms load time, no GPU required, runs on CPU . Can run pure-lexical ENGRIM EMBED=off for zero extra dependencies. - POSIX File Permissions : Databases are created with restricted owner-only permissions 0600 . - Git Protection : .db is gitignored by default; your memories never accidentally commit to version control. MIT © 2026 Tim Gordon.