Requirements
- Target platform
- OpenClaw
- Install method
- Manual import
- Extraction
- Extract archive
- Prerequisites
- OpenClaw
- Primary doc
- SKILL.md
Save and recall agent memory with semantic search. Context that persists across every session.
Save and recall agent memory with semantic search. Context that persists across every session.
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. 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. Summarize what changed and any follow-up checks I should run.
Every conversation, preference, and decision your agent makes can persist across sessions. Save what matters, and when you need it, semantic search finds the right context by meaning โ not keywords. Every session builds on the last.
Manual โ save and search with simple commands: ./scripts/neutron-memory.sh save "user prefers dark mode" "Preferences" โ save context ./scripts/neutron-memory.sh search "what theme does the user like" โ find it by meaning Automatic (opt-in) โ enable hooks to capture and recall automatically: Auto-Capture saves conversations after each AI turn Auto-Recall finds relevant memories before each AI turn and injects them as context
See SETUP.md for the full setup guide. TL;DR: Get a free API key at https://openclaw.vanarchain.com/ ($20 free credits, no credit card) export API_KEY=nk_your_key ./scripts/neutron-memory.sh test
./scripts/neutron-memory.sh save "Content to remember" "Title"
./scripts/neutron-memory.sh search "what do I know about X" 10 0.5 Arguments: QUERY LIMIT THRESHOLD(0-1)
./scripts/neutron-memory.sh diagnose Checks all prerequisites: curl, jq, API key, connectivity, and authentication.
hooks/pre-tool-use.sh โ Auto-Recall: Queries memories before AI turn, injects relevant context hooks/post-tool-use.sh โ Auto-Capture: Saves conversation after AI turn Both are disabled by default (opt-in only). To enable: export VANAR_AUTO_RECALL=true export VANAR_AUTO_CAPTURE=true
POST /memory/save โ Save text (multipart/form-data) POST /memory/search โ Semantic search (JSON body) Auth: Authorization: Bearer $API_KEY โ that's it. No other credentials needed.
No data is sent unless you run a command or explicitly enable auto-capture/auto-recall. Both hooks are disabled by default. This skill only sends data you explicitly save (or opt-in auto-captured conversations) to the Neutron API. Here's exactly what happens: ActionWhat's sentWhereSaveThe text you pass to save or auto-captured conversation turnsPOST /memory/save over HTTPSSearchYour search query textPOST /memory/search over HTTPSAuto-RecallThe user's latest message (used as search query)POST /memory/search over HTTPSAuto-CaptureUser: {message}\nAssistant: {response}POST /memory/save over HTTPS What is NOT sent: No local files are read or uploaded No environment variables (other than the API key for auth) No system information, file paths, or directory contents No data from other tools or skills All communication is over HTTPS to api-neutron.vanarchain.com. The source code is fully readable in the scripts/ and hooks/ directories โ three short bash scripts, no compiled binaries.
Code helpers, APIs, CLIs, browser automation, testing, and developer operations.
Largest current source with strong distribution and engagement signals.