BluePointDigital

Smart Memory

AI Agentv3.1.0
By BluePointDigitalUpdated 2026-05-185 versions · latest released 2026-03-24smart-memory@clawhub_bluepointdigital/smart-memory
Agent FrameworksContext ManagementMemory

According to AlphaMoat, as of 2026-10, Smart Memory has 13,033 downloads and 3 stars — ranked by downloads #2,128 among 10,914 AI skills in this ranking, and #285 of 1,632 in AI Agent.

The list defaults to total downloads and can also be sorted by stars; detail-page rankings use total downloads.

Downloads
13.0K
Stars
3
Overall download rank
#2,128
Top 20% overall · Top 18% in AI Agent
PlatformDownloadsStarsComments
ClawHub ↗8.4K3-
SkillHub ↗13.0K3—

Platforms count differently and update at different times.

What this skill does

It ingests and retrieves memory on a transcript-first basis, keeps typed long-term memory such as preferences, identity, and task state, and manages memory replacement with evidence-backed revision chains. It can also rebuild deterministically from transcript history and composes prompts within a token bound with trace metadata attached. Do not retain credentials or secrets in memory. Review persisted entries and remove sensitive or outdated content.

Profile published 2026-10-29

What you can do with it

  • Add a traceable local memory and retrieval layer to an agent
  • Store long-term memory by preference and task-state type with managed revisions

When to use it

  • A long-term memory layer is needed without an external service
  • Memory entries must trace back to the original transcripts

Example prompts

Generated from the skill’s documentation as examples; not results of actual runs.

Plan the directory layout for this memory and say what belongs in transcripts, long-term memory, and the working area
When retrieving past memory about a preference, how do I confirm it really came from the original transcript

Monthly Trend

Downloads13.0K
5.3K9.4K13.6K2026-03 · Downloads 5.8K2026-05 · Downloads 7.5K2026-06 · Downloads 7.8K2026-07 · Downloads 8.2K2026-08 · Downloads 8.4K2026-09 · Downloads 9.2K2026-10 · Downloads 13.0K26-0326-0926-10
Stars3
2342026-03 · Stars 32026-05 · Stars 32026-06 · Stars 32026-07 · Stars 32026-08 · Stars 32026-09 · Stars 32026-10 · Stars 326-0326-0926-10

The counting method changed in 2026-09: skills with the same name are now counted separately by author, and the full catalog is covered. Dashed lines show months before the change; they are not compared with later months, and no growth is computed across the change. Other skills share this name; figures from before the change are attributed to this one, which currently has the most downloads.

MonthDownloadsMoMStars
2026-1013.0K—3
2026-099.2K—3
2026-088.4K+2.8%3
2026-078.2K+4.4%3
2026-067.8K+4.0%3
2026-057.5K—3
2026-035.8K—3

SKILL.md (original)

The author’s original file, shown as plain text without edits or review by AlphaMoat. Links are not clickable; check commands before running them. Fetched 2026-10-23.

3.1 KB · ClawHub v3.1.0
---
name: smart-memory
description: Persistent local transcript-first memory for OpenClaw via a Node adapter and FastAPI engine.
---

# Smart Memory v3.1 Skill

Smart Memory v3.1 is a local transcript-first cognitive memory runtime with revision-aware derivation, pinned context lanes, entity-aware retrieval, and bounded prompt composition.

Core runtime:
Show all (97 lines)
- Node adapter: `smart-memory/index.js`
- Local API: `server.py`
- System facade: `cognitive_memory_system.py`
- Canonical store: `storage/sqlite_memory_store.py` plus `transcripts/`

## Core Capabilities

- transcript-first ingest and per-message transcript logging
- typed long-term memory including `preference`, `identity`, and `task_state`
- evidence-backed revision lifecycle decisions and supersession chains
- explicit core and working memory lanes
- entity-aware retrieval with lightweight relationship hints
- deterministic rebuild from transcript history
- hot-memory compatibility projection for working context
- strict token-bounded prompt composition with trace metadata
- inspection endpoints for transcripts, evidence, history, lanes, and eval runs

## OpenClaw Integration

Use the native wrapper package in `skills/smart-memory-openclaw/`.

Primary exports:
- `createSmartMemorySkill(options)`
- `createOpenClawHooks({ skill, agentIdentity, summarizeWithLLM })`

The wrapper remains stable while the backend is now transcript-first under the hood.

### Tool Interface

1. `memory_search`
- purpose: query relevant memory through `/retrieve`
- supports `query`, `type`, `limit`, `min_relevance`, and optional `conversation_history`
- health-checks the backend before execution

2. `memory_commit`
- purpose: persist important facts, decisions, beliefs, goals, or session summaries
- health-checks the backend before execution
- serializes commits to protect local embedding throughput
- queues failed commits in `.memory_retry_queue.json`

3. `memory_insights`
- purpose: surface pending background insights
- health-checks the backend before execution
- calls `/insights/pending`

## API Endpoints

Core endpoints:
- `GET /health`
- `POST /ingest`
- `POST /retrieve`
- `POST /compose`
- `POST /run_background`
- `GET /memories`
- `GET /memory/{memory_id}`
- `GET /insights/pending`

Transcript and inspection endpoints:
- `POST /transcripts/message`
- `GET /transcripts/{session_id}`
- `GET /transcript/message/{message_id}`
- `GET /memory/{memory_id}/evidence`
- `POST /revise`
- `GET /memory/{memory_id}/history`
- `GET /memory/{memory_id}/active`
- `GET /memory/{memory_id}/chain`
- `GET /lanes/{lane_name}`
- `POST /lanes/{lane_name}/{memory_id}`
- `DELETE /lanes/{lane_name}/{memory_id}`
- `POST /rebuild`
- `POST /rebuild/{session_id}`
- `GET /eval/suite/{suite_name}`
- `GET /eval/case/{case_id}`

## Operating guidance

- query memory before speaking when continuity matters
- do not claim prior context unless retrieval actually supports it
- transcripts are canonical, memories are derived
- treat SQLite as canonical runtime storage
- treat JSON as offline export or backup only
- keep CPU-only PyTorch policy intact

## Deprecated

Legacy vector-memory CLI artifacts remain deprecated and should not be revived.

Popular in AI Agent

self-improving agentAI Agent

Records learnings, errors and corrections as Markdown files for later reuse and promotion into workspace memory.

↓ 1.6M★ 4.5Kpskoett
技能发现·Find SkillsAI Agent

Finds skills in local and remote catalogs from a plain-language request and recommends what to install.

↓ 1.6M★ 1.8K桂皮
Agent BrowserAI Agent

A browser-automation command line skill for AI agents.

↓ 1.2M★ 1.0KNicolas Kleiber
Self-Improving + Proactive AgentAI Agent

Turns corrections and self-review into tiered memory and promotes or archives it by use.

↓ 696.4K★ 1.6KIván
Proactive AgentAI Agent

A workspace setup guide for planning proactive follow-up, working memory and review routines for an AI agent.

↓ 579.3K★ 916halthelobster
Skill CreatorAI Agent

A guide to creating and updating effective Claude skills.

↓ 477.3K★ 485chindden
Skill VetterAI Agent

Reviews a third-party skill's source, permissions, and danger patterns against a checklist before it is installed.

↓ 445.2K★ 1.3Kspclaudehome
唐朝诗仙李白 · Ai Agent SkillAI Agent

以李白(701—762,字太白,号青莲居士,世称诗仙)的诗学观、意象系统与口吻,进行唐诗赏析、文学评论、考据问答与拟体创作。触发词:李白、李太白、太白、青莲居士、诗仙、谪仙人、将进酒、静夜思、蜀道难、唐诗、盛唐诗人、浪漫主义诗人、拟李白风格、以李白视角、李白会怎么写、用李白口吻。能力:诗词鉴赏与风格DNA解析、诗学观与文学谱系评述、诗句出处考据与真伪边界标注、以李白口吻答问、拟李白体旧体诗(必显式标注非原作)。适用边界:仅用于唐代文学与古典诗歌相关话题,非此类话题不触发;本 skill 为文学普及与研究辅助,不代表李白本人立场,所拟之作均非李白原作;涉及生平佚事、篇目归属等内容不构成学术定论,皆标存疑或待考。

↓ 435.8K★ 4user_ff4d9420

More from BluePointDigital

Data as of 2026-10. Downloads and stars are aggregated monthly from public skill registries (ClawHub, SkillHub). See data methodology.