Requirements
- Target platform
- OpenClaw
- Install method
- Manual import
- Extraction
- Extract archive
- Prerequisites
- OpenClaw
- Primary doc
- SKILL.md
Agent memory with ALMA meta-learning, LLM fact extraction, and full-text search. Observer calls remote LLM APIs (OpenAI/Anthropic/Gemini). ALMA and Indexer w...
Agent memory with ALMA meta-learning, LLM fact extraction, and full-text search. Observer calls remote LLM APIs (OpenAI/Anthropic/Gemini). ALMA and Indexer w...
Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.
I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Then review README.md for any prerequisites, environment setup, or post-install checks. Tell me what you changed and call out any manual steps you could not complete.
I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Then review README.md for any prerequisites, environment setup, or post-install checks. Summarize what changed and any follow-up checks I should run.
Three components for agent memory: ALMA โ Evolves memory designs through mutation + evaluation (offline) Observer โ Extracts structured facts from conversations via LLM API (requires API key) Indexer โ Full-text search over workspace Markdown files (offline)
Observer requires one of: OPENAI_API_KEY ANTHROPIC_API_KEY Or pass apiKey in config ALMA and Indexer require no keys or network access.
Proposes memory system designs, evaluates them, keeps the best. Uses gaussian mutation and simulated annealing to explore the design space. alma.propose() โ design alma.evaluate(design.id, metrics) โ score alma.best() โ top design alma.top(5) โ leaderboard
Sends conversation history to an LLM, gets back structured facts: Kind: world fact / biographical / opinion / observation Priority: high / medium / low Entities: mentioned people/places Confidence: 0.0โ1.0 for opinions Fails gracefully โ returns empty array if LLM is unavailable.
Chunks workspace Markdown files and indexes them for search: MEMORY.md โ core facts memory/YYYY-MM-DD.md โ daily logs bank/entities/*.md โ entity summaries bank/opinions.md โ beliefs with confidence indexer.index() โ count of chunks indexed indexer.search('query') โ ranked results indexer.rebuild() โ re-index from scratch
npm install @artale/openclaw-memory
Indexer uses an in-memory mock database, not real SQLite FTS5. Search works but ranking is simplified. Observer calls remote APIs โ not offline. Only ALMA and Indexer work without network. No dashboard โ removed in v2 for simplicity.
5 files, 578 lines, 0 runtime dependencies. https://github.com/arosstale/openclaw-memory
Code helpers, APIs, CLIs, browser automation, testing, and developer operations.
Largest current source with strong distribution and engagement signals.