claude-memory-kit
Persistent memory for Claude Code agents with an agent-audit-ritual architecture. User only talks; agent captures, audits, proposes promotions, and writes. Four layers — daily logs, hot cache (MEMORY.md), role-based reference skills (Anthropic-native, user-invocable: false), canonical rules. /close-day runs the audit ritual at end of day. Multi-project isolation via projects/<name>/. Zero external dependencies.
- License 许可
- MIT
- 最近更新
- 2026-11-12
- Stars
- ★ 4
- Forks
- 0
01 前言 Front Matter
- name
- claude-memory-kit
- tags
- [ "memory", "context-management", "productivity", "claude-code", "agent-memory", "knowledge-base", "reference-skills", "multi-project" ]
- author
- awrshift
- license
- MIT
- version
- 4.0.0
- repository
- https://github.com/awrshift/claude-memory-kit
- description
- Persistent memory for Claude Code agents with an agent-audit-ritual architecture. User only talks; agent captures, audits, proposes promotions, and writes. Four layers — daily logs, hot cache (MEMORY.md), role-based reference skills (Anthropic-native, user-invocable: false), canonical rules. /close-day runs the audit ritual at end of day. Multi-project isolation via projects/<name>/. Zero external dependencies.
02 资源文件 14
- 参考文档_filelist.txt356 B
- 参考文档.kit/ARCHITECTURE.md15.7 KB
- 参考文档.kit/CHANGELOG.md23.4 KB
- 参考文档.kit/CONTRIBUTING.md2.9 KB
- 参考文档CLAUDE.md10.2 KB
- 参考文档context/next-session-prompt.md2.2 KB
- 参考文档daily/README.md1.0 KB
- 参考文档daily/TEMPLATE.md1.7 KB
- 参考文档experiments/EXPERIMENT-TEMPLATE.md1.6 KB
- 参考文档experiments/README.md2.7 KB
- 参考文档knowledge/index.md2.2 KB
- 参考文档knowledge/log.md158 B
- 参考文档projects/my-first-project/BACKLOG.md3.3 KB
- 参考文档README.md7.5 KB
03 SKILL.md 正文
Claude Memory Kit v4
Persistent memory for Claude Code agents. Four-layer architecture, agent-driven promotion, zero manual file editing.
Core invariant
User only talks. Agent captures, proposes, writes. Every architectural decision passes this test.
What's different from v3.2
- Agent-driven promotion ritual via
/close-day(was: backgroundpromote-patterns.pydetection, killed as unreliable) - Role-based reference skills (
.claude/skills/<role>-guidance/SKILL.mdwithuser-invocable: false) alongside topic-basedknowledge/concepts/— two axes, no overlap. Uses Anthropic-native auto-invoke viadescriptionmatching — no custom trigger tables. - Multi-project isolation via
projects/<name>/— shared layers load always, per-project scope on demand /memory-auditoperator for oversized-reference-skill detection + semantic split execution- Killed:
experiences/staging layer,promote-patterns.pybackground script,flush.pyauto-flush, separateplaybooks/directory (merged into reference skills)
See CHANGELOG.md for full migration notes.
Quick start
git clone https://github.com/awrshift/claude-memory-kit.git my-project
cd my-project
claude
First session: agent greets you, asks 2-3 setup questions, loads you in. Type /tour for a guided walkthrough.
Daily workflow
- Open a session — hooks auto-load NSP + MEMORY + knowledge index
- Work normally — agent captures patterns in MEMORY.md as you speak
/close-daywhen done — agent synthesizes today, audits for promotions, proposes verbally, writes on your verbal "yes"
Tomorrow starts where today left off.
Included skills
| Skill | Description |
|---|---|
/close-day |
End-of-day audit ritual: synthesis + promotion proposals |
/memory-audit |
Oversized-reference-skill structural check + split proposals |
/memory-lint |
Hygiene (broken links, sparse articles, orphans, oversized reference skills) |
/memory-compile |
Compile daily logs into knowledge/concepts/ articles |
/memory-query |
Natural-language search across all memory layers |
/tour |
Interactive guided walkthrough |
Architecture
Four layers, each with its own purpose:
| Layer | Answers | Written by |
|---|---|---|
daily/YYYY-MM-DD.md |
«what happened today» | /close-day |
.claude/memory/MEMORY.md |
«what patterns repeat across sessions» | agent as you speak |
.claude/skills/<role>-guidance/SKILL.md |
«how should a <role> think about X» | /close-day promotion |
.claude/rules/*.md |
«what must always / never happen» | /close-day after 6+ months stable |
See ARCHITECTURE.md for full details and CLAUDE.md for the agent's session workflow.
Built from production use
Iteration on 700+ real sessions across 7+ projects. Every component earns its place; experiences/ and background-detection scripts didn't survive review.
04 同仓库更多 Skills
agentic-ecology-ui
Guidelines and templates for creating a generic web UI to visualize, rank, filter, and annotate vector databases. The UI has a hierarchical structure covering database selection, label selection/definition, ranking/filtering configuration, and row visualization/annotation. Use when building, serving, or adapting an interactive web UI for Hoplite vector databases.
agentic-ecology-init
Initializes a local uv-managed project directory for agentic ecology workloads. Sets up Python dependencies using reference pyproject.toml and uv.lock, configures workspace rules, and ensures Agentic Ecology skills are discoverable. Use when initializing a new project workspace or bootstrapping a clean environment.
agentic-ecology-camera-traps
Provides capabilities to run SpeciesNet detector and classifier on camera trap images, extract crop-level feature embeddings, and populate a Hoplite vector database for downstream search and agile modeling. Use when ingesting camera trap images, classifying wildlife photos, or indexing camera trap data.
agentic-ecology-bioacoustics
Provides bioacoustic analysis capabilities for ecologists and researchers using the perch-hoplite Python package. A typical use case is to use agile modeling to bootstrap the creation and deployment of a bespoke detector for targeted species on an existing collection of passive acoustic monitoring recordings. Use when processing and annotating audio recordings for bioacoustic applications.
sample-skill
Sample skill used by agent-env integration tests. Exercises SKILL.md parsing plus supporting scripts and references.
simready-foundation-validate-foundation-change
Use for auditing SimReady requirement, validator, feature, profile, adapter, test, and skill consistency.