toejough/engram

Self-correcting memory for LLM agents. A Claude Code plugin that learns from sessions, surfaces relevant memories, measures whether they're actually followed, and fixes the ones that aren't.

8Stars on the repository
25Mods indexed here, across every type
yesterdayLast push, which is what freshness is scored on
Apache-2.0Licence, which decides whether bodies are shown

commit

01

toejough/engram

Command Claude Code

Create a git commit with proper formatting and AI-Used trailer.

8 yesterday A 12 tokens original Apache-2.0

OPSX: Apply

02

toejough/engram

Command Claude Code

Implement tasks from an OpenSpec change (Experimental).

8 yesterday A 15 tokens copy · 81% Apache-2.0

OPSX: Archive

03

toejough/engram

Command Claude Code

Archive a completed change in the experimental workflow.

8 yesterday A 13 tokens copy · 86% Apache-2.0

OPSX: Explore

04

toejough/engram

Command Claude Code

Enter explore mode - think through ideas, investigate problems, clarify requirements.

8 yesterday A 18 tokens copy · 95% Apache-2.0

OPSX: Propose

05

toejough/engram

Command Claude Code

Propose a new change - create it and generate all artifacts in one step.

8 yesterday A 21 tokens copy · 81% Apache-2.0

OPSX: Sync

06

toejough/engram

Command Claude Code

Sync delta specs from a change to main specs.

8 yesterday A 14 tokens copy · 83% Apache-2.0

OPSX: Update

07

toejough/engram

Command Claude Code

Update a change - revise existing planning artifacts and keep them coherent (Experimental).

8 yesterday A 20 tokens copy · 80% Apache-2.0