Your coding agent has amnesia. Here's the memory architecture that fixes it.

Description and use

Engraphis provides durable, scoped, provenanced memory for coding agents, reducing context size and enabling agents to recall decisions without re‑entering them.

Problem

Coding agents lose durable project knowledge when context windows are compacted or sessions end, causing them to forget prior decisions and propose incorrect actions.

Outcome

Engraphis reduces retrieved context tokens by 71.1% on deterministic fixtures, provides durable, scoped, provenanced memory, and enables agents to cite decisions and avoid repeating past mistakes.

Workflow

• 1. Install Engraphis MCP or dashboard.
• 2. Initialize memory service with a local SQLite database.
• 3. Use engraphis_remember to store decisions with workspace, repo, and provenance.
• 4. Use engraphis_recall_context to retrieve compact, scoped context for the current task.
• 5. Agent uses retrieved context to inform decisions and can cite provenance or abstain if uncertain.

Evidence

A coding agent has three kinds of state: the current task, the working context, and durable project knowledge that must survive the session.

Source

Engraphis is deliberately boring at the storage layer and careful at the retrieval layer.

Source

The result is the same: the agent has information, but not context with provenance.

Source

Mean retrieved context dropped from 740.3 to 214.3 tokens per question — a 71.1% reduction across 18 questions.

Source