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.
- 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 growthMomentum uses available readings from the last 7 days: measured with at least two comparable readings, estimated otherwise.
Reading history
| Date | Value | Metric |
|---|---|---|
| 33 | GitHub stars | |
| 33 | GitHub stars | |
| 31 | GitHub stars |
Classifications
- Domains
- Type
- Agent skills
- Use cases