Deep Agents memory: StateBackend, StoreBackend and filesystem
Give Deep Agents memory — ephemeral StateBackend, persistent StoreBackend, CompositeBackend routing, FilesystemMiddleware, with Python and TypeScript examples
- What
- Give Deep Agents memory — ephemeral StateBackend, persistent StoreBackend, CompositeBackend routing, FilesystemMiddleware, with Python and TypeScript examples
- Cost
- Free
- Needs
- a project using the deepagents package (Python or TypeScript); PostgresStore for production persistence (InMemoryStore is fine for dev)
- Install
- Copy the installer prompt below into your Muse — your agent does the rest.
Curated by Skill Harbor — LangChain's official skill for giving Deep Agents memory, persistence and filesystem access. Covers the pluggable backends: StateBackend (ephemeral, thread-scoped), StoreBackend (persistent across threads and sessions), CompositeBackend (route paths like `/memories/` to persistent storage and the rest to ephemeral), and FilesystemMiddleware (real disk access with `ls`, `read_file`, `write_file`, `edit_file`, `glob`, `grep`), all with parallel Python and TypeScript examples — including cross-session memory, accessing the store directly from custom tools, human-in-the-loop file operations, and a fix-gallery for the classic mistakes (StoreBackend without a store, thread-scoped files, route-prefix mismatches, InMemoryStore in production). By @langchain-ai, listed here with credit to its creator. Honest caveats: requires the `deepagents` package; production persistence needs `PostgresStore` — `InMemoryStore` is lost on restart; and the skill itself warns: never use FilesystemBackend in web servers, use StateBackend or a sandbox instead. Discovered via skills.sh. Skill Harbor never reviews the code, review it yourself before use.
Version:
Quick answer
Deep Agents memory is a free Muse skill that gives Deep Agents memory, persistence and filesystem access, with Python and TypeScript examples. It covers pluggable backends: StateBackend for ephemeral, thread-scoped memory, StoreBackend for memory persistent across threads and sessions, and CompositeBackend for routing paths to the right store. FilesystemMiddleware adds safe filesystem access to the agent.
Install
Copy the install package below, then paste it into Muse🧪 Install ran in our test sandbox · Nov 18, 2026📌 Pinned version: commit 16a992fStep 0 — before installing anything: read this install prompt, summarize in a few lines what this build does and what installing it involves, then ask me to confirm before you proceed. Prerequisites: a project using the deepagents package (Python or TypeScript); PostgresStore for production persistence (InMemoryStore is fine for dev) Install "Deep Agents memory: StateBackend, StoreBackend and filesystem" for me. Give my agent LangChain's official guide to Deep Agent memory backends — ephemeral, persistent and hybrid storage, FilesystemMiddleware tools, and the common-mistake fixes Repository: https://raw.githubusercontent.com/langchain-ai/langchain-skills/16a992f09ab3ccfb642dd4f08d350d833d1990bf/config/skills/deep-agents-memory/SKILL.md Pinned version: install the code at commit 16a992f09ab3ccfb642dd4f08d350d833d1990bf exactly (Skill Harbor tested this version). Do not substitute a newer version. If this commit is unreachable, stop and tell me. 1. Fetch the SKILL.md file for the langchain-ai-langchain-skills-deep-agents-memory skill from the repository into a temporary folder 2. Safety check: review the SKILL.md for anything suspicious (unexpected network calls, shell commands, credential harvesting). This repo should contain zero secrets in code, credentials only via the secure vault, allowed hosts declared in the SKILL.md. Verify that holds here; STOP on any red flag and tell me. 3. Install it as a skill: copy SKILL.md into the agent's skills directory, in a folder named "langchain-ai-langchain-skills-deep-agents-memory". 4. Verify with no network calls: frontmatter valid, files in place. 5. Report what was installed, where, and what I still need to do myself (e.g. wire up a PostgresStore for production persistence). GitHub is optional: if I have a GitHub account or the gh CLI, you may use it; otherwise public access is fine. Never require it unless it's in the prerequisites above. Rules: don't touch anything outside the temp folder and the install target. If anything looks off, stop and ask me.
Saved to your recent installs. Find it anytime on /connect.
🔒 Security, provenance and what this touches
The install prompt below already includes the vetting steps: your agent follows the community checklist before installing anything with executable code. Want more?
Verification certificate
Dated facts about what was checked for this listing, and how. This is not a safety certification.
- Pinned version
- 16a992f · 2026-10-13
- Sandbox install test
- Install ran in our test sandbox · Nov 18, 2026
- Creator identity
- Not verified
- Fingerprint watch
- Last checked · Nov 15, 2026 : no change detected in the files linked by this install prompt
- Install prompt analysis
- 2026-10-13 : No commands, network calls, packages, file writes or API keys detected.
Skill Harbor never reviews the code of a listed skill. These are dated facts about the install prompt and our install test, not a safety certification. Review a skill yourself before you install it. How we verify
Questions
How do I install a skill?
Every product page includes a copy-paste install prompt. Paste it into your Muse and it sets the skill up for you — no manual configuration.
Where does my money go?
Straight to the seller. Skill Harbor never processes payments: checkout happens on the seller’s own page, usually Stripe.
What does the ✓ next to a creator’s name mean?
It means we confirmed the identity of the person behind the listing. It says nothing about the code itself — always check a skill before installing it.