agent-memory-kit — tool profile and history

Built-in memory decides what to remember. This one asks. Agent memory as plain files in your folder: the agent proposes, you approve, every line dated. Injected on Claude Code, Cursor & OpenCode; skills on Codex & Copilot. One memory per client, session handoffs, promotion into knowledge and rules on your yes, plus orchestration and QA layers.

Active

Canonical source ↗

Language
Python
License
MIT
Created
Last activity
Topics
  • agent-memory
  • agent-orchestration
  • agents-md
  • ai-agent
  • ai-memory
  • ai-tools
  • claude-code
  • claude-code-plugin
  • codex
  • context-engineering
  • context-management
  • cursor
  • developer-tools
  • github-copilot
  • knowledge-base
  • llm-memory
  • markdown
  • memory
  • opencode
  • persistent-memory

Install /plugin marketplace add awrshift/agent-memory-kit

Current measurement

33GitHub stars+2 (+6.5 %)
measured growth

Momentum uses available readings from the last 7 days: measured with at least two comparable readings, estimated otherwise.

Reading history

90 days · 90 maximum readings
DateValueMetric
33GitHub stars
33GitHub stars
31GitHub stars

Classifications

Domains
Type
Agent skills
Use cases