timgordontg/engrim

The Universal Cross-Model & Cross-Agent Episodic Memory Standard.
A local-first, project-scoped SQLite memory engine that allows developers to freely switch between models and environments (Google Antigravity, Claude Code, Cursor, Codex CLI, GitHub Copilot CLI, OpenCode, and Windsurf) on the same codebase without losing architectural decisions, user constraints, or project state.
## 1. Overview & Core Value Proposition
> "Why pay for 200,000 tokens of forgotten noise on every turn? The models are disposable utilities; your project's decisions are not."
Engrim is the universal, cross-model episodic memory standard engineered specifically for autonomous AI coding agents and heavy software development.
It solves the "200,000-token context window trap" (where coding models suffer from severe attention dilution, compounding per-turn token costs, and the loss of prior architectural decisions whenever a chat session is cleared) by replacing raw transcript replay with 4,000 characters of high-precision, curated episodic working memory stored in a single, local-first SQLite file (~/.engrim/memory.db).
### The Problem vs. The Engrim Standard
| Challenge | Without Engrim (Token Bloat & Context Resets) | With Engrim (Episodic Continuity) |
| Context Window | Attention Dilution: 150k+ tokens re-sent on every turn; models lose reasoning sharpness and hallucinate past constraints. | Precision Working Memory: ~4,000 chars ( (PreInvocation & Stop Hooks)"]
CLAUDE["Claude Code (SessionStart & Stop Hooks)"]
CURSOR["Cursor / Windsurf (Model Context Protocol stdio)"]
CODEX["Codex CLI (Hooks, guidance & optional MCP)"]
OPENCODE["OpenCode (Plugin & MCP)"]
COPILOT["GitHub Copilot CLI (Command hooks & MCP)"]
end
subgraph CoreEngine ["engrim Core Engine (v1.4.11)"]
ADAPTERS["Adapters & Lifecycle Hooks (agy, claude, opencode, copilot, mcp)"]
DOCTOR["Health & Diagnostic Engine (engrim doctor --fix)"]
PROVENANCE["Agent Provenance Engine (originagent tracking)"]
ROUTER["Hybrid Retrieval & Minder (bm25 lexical + vector cosine)"]
end
subgraph Storage ["Local-First SQLite Store (~/.engrim/memory.db)"]
MEMORIES[("Curated Memories (decisions, facts, feedback)")]
FTS5["FTS5 Full-Text Search (porter stemmer, triggers)"]
VEC["Vector Embeddings (model2vec static embeddings)"]
LOG["Flight Recorder Log (turns + action lines)"]
end
AGY |"hook / CLI"| ADAPTERS
CLAUDE |"hook / CLI"| ADAPTERS
CURSOR |"JSON-RPC (stdio)"| ADAPTERS
CODEX |"command hook / MCP"| ADAPTERS
OPENCODE |"plugin / MCP"| ADAPTERS
COPILOT |"command hook / MCP"| ADAPTERS
ADAPTERS --> PROVENANCE
PROVENANCE --> ROUTER
ROUTER --> MEMORIES
MEMORIES --- FTS5
MEMORIES --- VEC
ADAPTERS --> LOG
1. Boot: When your agent starts or a prompt is submitted, engrim injects the top-priority memory pack (~4k chars) into the agent's context, leading with [▶ RESUME HERE].
2. Capture: As the agent works, it records architectural decisions via MCP (engrimadd) or lifecycle hooks automatically, tracking the originagent provenance.
3. Recall & Minder: Hybrid lexical (bm25) + vector (model2vec) search retrieves relevant records on demand in ~30ms without slowing down the agent.
4. Continue-As-Clear: When context bloats or the model drifts, type /clear. The next session boots from memory.db with zero memory loss.