awrshift/agent-memory-kit

One memory for every coding agent — plain markdown in your repo. Injected on Claude Code & Cursor, skills on Codex & Copilot, plugin for OpenCode. Dated, capped, audited: agent memory that doesn't rot. Session handoffs, human-approved promotion into knowledge and rules, plus orchestration and QA layers.

31Stars on the repository
19Mods indexed here, across every type
yesterdayLast push, which is what freshness is scored on
MITLicence, which decides whether bodies are shown

SessionStart

01

awrshift/agent-memory-kit

Hook

Runs when a session starts on startup, clear, resume, compact and fork, executing session-start.py via python3. From awrshift/agent-memory-kit.

31 yesterday A tokens not measured copy · 100% MIT

PreToolUse

02

awrshift/agent-memory-kit

Hook

Runs before the agent uses a tool for Edit and Write tool calls, executing protect-tests.py via python3. From awrshift/agent-memory-kit.

31 yesterday A tokens not measured copy · 100% MIT

PreCompact

03

awrshift/agent-memory-kit

Hook

Runs before the context is compacted, executing pre-compact.sh via bash. From awrshift/agent-memory-kit.

31 yesterday A tokens not measured copy · 55% MIT

SessionEnd

04

awrshift/agent-memory-kit

Hook

Runs when a session ends, executing session-end.sh via bash. From awrshift/agent-memory-kit.

31 yesterday A tokens not measured copy · 48% MIT