Atxp Memory
- 721 installs
- 10 repo stars
- Updated April 27, 2026
- atxp-dev/cli
atxp-memory is a Claude Code skill that backs up, restores, and semantically searches .md agent memory files for developers who need persistent context across long or interrupted coding sessions.
About
atxp-memory is an agent memory management skill from the atxp-dev/cli package for Node.js >=18 environments using npx. It handles cloud backup and restore of .md memory files via ATXP_CONNECTION authentication (from npx atxp@latest login or agent register), plus local vector search powered by zvec indexing. Local index and search work without cloud credentials; push, pull, and status require the auth token. Developers reach for atxp-memory when agents lose thread across sessions, when identity or project context must survive machine changes, or when prior decisions buried in markdown need semantic retrieval instead of manual grep. The skill fits agent-heavy workflows where memory files are the source of truth for ongoing work.
- Cloud backup and restore of .md memory files to ATXP servers
- Local vector search over memories using embedded zvec database
- Status command showing cloud backup info and local index statistics
- Only .md files are transmitted — no credentials or binary files
- Works with or without cloud token for local-only index and search
Atxp Memory by the numbers
- 721 all-time installs (skills.sh)
- Ranked #1,396 of 16,546 AI & Agent Building skills by installs in the Skillselion catalog
- Data as of Jul 30, 2026 (Skillselion catalog sync)
npx skills add https://github.com/atxp-dev/cli --skill atxp-memoryAdd your badge
Show developers this skill is listed on Skillselion. Paste this into your README.
| Installs | 721 |
|---|---|
| repo stars | ★ 10 |
| Last updated | April 27, 2026 |
| Repository | atxp-dev/cli ↗ |
How do you persist agent memory across sessions?
Keep persistent context across long agent sessions by backing up, restoring, and semantically searching.md memory files.
Who is it for?
Developers running long Claude Code or Cursor sessions who store agent context in markdown and need backup plus semantic recall.
Skip if: Projects with no .md memory files or teams that rely solely on chat history without structured agent memory.
When should I use this skill?
The user mentions agent memory backup, ATXP sync, zvec search, .md memory files, or losing context between sessions.
What you get
Backed-up .md memory files, restored session context, and semantically ranked search results from a local zvec index.
- synced .md memory archive
- local vector search index
By the numbers
- Requires Node.js >=18 and npx
- Uses zvec for local vector search of .md memory files
Files
ATXP Memory — Agent Memory Management
Manage your agent's .md memory files: back up and restore to/from ATXP cloud servers, and search your local memories using zvec vector similarity search.
Capabilities
| Capability | Description |
|---|---|
| Cloud Backup | Push/pull .md files to ATXP servers for disaster recovery |
| Local Search | Index .md files into a local zvec vector database, then search by natural language query |
| Status | View cloud backup info and local index statistics |
Security Model
- Only `.md` files are collected and transmitted (push/pull). No credentials, JSON configs, binaries, or other file types are ever sent.
- Files are sent to ATXP servers over HTTPS, associated with the authenticated agent's identity.
pushreplaces the server snapshot entirely (latest snapshot only, no history).pullis non-destructive — it writes server files to the local directory but does not delete local files absent from the server.- Local search index is stored in a
.atxp-memory-index/subdirectory inside--path. It never leaves the local machine. - index and search do not require authentication or network access.
- Filesystem access: reads from
--pathdirectory (push/index), writes to--pathdirectory (pull) and--path/.atxp-memory-index/(index). No other directories are touched. - No modification of OpenClaw config or auth files.
When to Use
| Situation | Command |
|---|---|
| After meaningful changes to SOUL.md, MEMORY.md, or at end of session | push |
| Bootstrapping a fresh workspace or recovering from environment loss | pull |
| After updating memory files and before starting a task that requires recall | index |
| Looking for relevant context in past memories | search |
| Verify backup exists before risky operations | status |
Commands Reference
| Command | Description |
|---|---|
npx atxp@latest memory push --path <dir> | Recursively collect all *.md files from <dir> and upload to server |
npx atxp@latest memory pull --path <dir> | Download backup from server and write files to <dir> |
npx atxp@latest memory index --path <dir> | Chunk .md files by heading and build a local zvec search index |
npx atxp@latest memory search <query> --path <dir> | Search indexed memories by similarity |
npx atxp@latest memory status [--path <dir>] | Show cloud backup info and/or local index stats |
Options
| Option | Required | Description |
|---|---|---|
--path <dir> | Yes (push/pull/index/search) | Directory to operate on |
--topk <n> | No (search only) | Number of results to return (default: 10) |
How Local Search Works
1. Indexing (memory index):
- Scans all
.mdfiles recursively from--path - Splits each file into chunks at heading boundaries (h1/h2/h3)
- Converts each chunk into a 256-dimensional feature vector using locality-sensitive hashing (unigrams + bigrams)
- Stores vectors and metadata in a local zvec database (HNSW index) at
<path>/.atxp-memory-index/
2. Searching (memory search):
- Converts the query text into the same vector representation
- Performs approximate nearest neighbor search via zvec's HNSW index
- Returns the top-k most similar chunks with file paths, headings, line numbers, and similarity scores
The search is purely local — no network requests, no API keys, no cost. Re-index after modifying memory files.
Path Conventions
Typical OpenClaw workspace paths:
~/.openclaw/workspace-<id>/
~/.openclaw/workspace-<id>/SOUL.md
~/.openclaw/workspace-<id>/MEMORY.md
~/.openclaw/workspace-<id>/memory/
~/.openclaw/workspace-<id>/AGENTS.md
~/.openclaw/workspace-<id>/USER.mdBackward Compatibility
The backup command is still accepted as an alias for memory:
npx atxp@latest backup push --path <dir> # works, same as memory push
npx atxp@latest backup pull --path <dir> # works, same as memory pull
npx atxp@latest backup status # works, same as memory statusLimitations
- `.md` files only — all other file types are ignored during push/index and not present in pull.
- Latest snapshot only — each push overwrites the previous backup. There is no version history.
- Requires ATXP auth for cloud operations — run
npx atxp@latest loginornpx atxp@latest agent registerfirst. - `--path` is required — there is no auto-detection of workspace location.
- Local search requires @zvec/zvec — install with
npm install @zvec/zvecbefore using index/search. - Feature-hash embeddings — local search uses statistical text hashing, not neural embeddings. It works well for keyword and phrase matching but is not a full semantic search. For best results, use specific terms from your memory files.
Related skills
Setup Matt Pocock SkillsScaffold the per-repo configuration that Matt Pocock’s engineering agent skills rely on so they understand the issue tracker, triage labels, and domain documentation la495k196k
Lark AppsConnect Claude, Cursor or custom agents directly to Lark (Feishu) for messaging, document automation, approval workflows and enterprise data access.402k
CavemanSlash token usage by roughly 75% while keeping every technical detail intact when working with Claude Code, Cursor or similar agents.391k94.7k
Lark Skill MakerQuickly turn any Lark/Feishu OpenAPI call or multi-step workflow into a reusable agent skill with its own SKILL.md.386k16k
Running Claude Code Via Litellm CopilotRun Claude Code at a fraction of the cost by routing requests through LiteLLM to the GitHub Copilot Chat API.270k72
Codex PetGenerate a complete Codex Pet spritesheet and metadata from one reference image without needing an OpenAI key or Codex Pro.246k10FAQ
Does atxp-memory require cloud authentication for all operations?
atxp-memory requires ATXP_CONNECTION only for cloud push, pull, and status operations. Local index and semantic search of .md memory files work without the auth token, enabling offline recall of agent context.
What runtime does atxp-memory need?
atxp-memory requires Node.js version 18 or higher and npx. Authentication tokens are created via npx atxp@latest login or agent register before cloud backup and restore operations.