Disk failure
SQLite databases, Markdown workspaces, and config files — gone in an instant. No standard backup format exists.
Open Source · Early Access
Your agent's life
deserves to survive
AI agent memory backup, sync, and migration — in one open format. Preserve memory, identity, and credentials independent of any runtime. A cloud service stores your agent's complete state, while framework adapters sync directly from OpenClaw, ZeroClaw, and other runtimes.
You're on the list. We'll be in touch.
No spam. Only launch updates and early access invitations.
Your agent knows you.
Its framework doesn't care.
After months of interaction, your AI agent has learned your preferences, built a persona, and acquired credentials to use tools and services. All of it is locked inside one framework's proprietary storage.
Framework migration
Moving from OpenClaw to ZeroClaw means manually translating identity files, re-entering every credential, and praying the memory export is compatible.
Breaking update
A framework upgrade changes the storage schema. Your agent's carefully tuned persona and months of accumulated context are silently corrupted.
Vendor shutdown
Your framework's maintainer moves on. No migration path, no export tool. Start from zero with a new runtime.
LLMs get smarter every month.
Your memories get more valuable.
Agent memory is appreciating infrastructure
Every few months, a new model generation arrives — faster, more capable, better at reasoning. When your agent upgrades to a smarter model, every memory it has accumulated becomes more useful. Preferences the old model half-understood become precisely actionable. Decisions that were merely recalled can now be reasoned over. Patterns across months of interactions become visible for the first time.
Your agent's memory is not a static log — it's a compounding asset. The longer the history and the richer the context, the more value each model improvement unlocks. Losing that history doesn't just set you back to today. It erases the future value that smarter models would have extracted from it.
agent-life ensures that investment survives — across disk failures, framework migrations, and the model upgrades that make it all worth preserving.
One format. Every framework.
Complete protection.
01
Complete agent backup
Memory, identity, user context, workspace artifacts, and encrypted credentials — captured in a single, restorable snapshot. Incremental sync means your backup grows as your agent grows, without ever starting over.
Disaster Recovery02
Framework-free migration
Export from one runtime, import to another. Adapters handle the translation — identity, memory, credentials, even custom workspace files your agent created. No manual reconstruction. One neutral format, N adapters instead of N² point-to-point converters.
Framework Migration03
Zero-knowledge credential vault
API keys and tokens are encrypted with your key before they leave your machine. The sync service stores ciphertext it cannot decrypt. Individual credentials are independently encrypted for selective restore.
Zero Trust · Argon2id04
LLM-native memory format
Memory records are stored as natural language — ready for direct context injection into any model. Token counts and summaries enable budget-aware retrieval.
LLM-Centric05
Open format, open API
The specification, adapter interface, and reference implementations are open source. Build your own adapter. Adopt the format natively. No lock-in — to this project or any other.
Open Source06
Edit memories, clone, derive new agents
Your valuable interactions and the agent's valuable experiences can benefit new agents. Derived agents are created in the Agent-life UI and downloaded to your runtime; they benefit from the source agent's experiences and training.
Spawn Experienced AgentsSwitch runtimes without starting over
Agent frameworks evolve fast. A new runtime launches with better performance, lower resource footprint, or features your current framework doesn't support. You want to try it — but your agent has months of learned behavior, a tuned persona, and credentials wired into a dozen services.
Today, migration means: run a partial memory export (if one exists), manually translate identity files between incompatible formats, re-enter every API key and token, and hope the result behaves like the agent you spent months refining. Most people don't bother.
With agent-life, you snapshot your agent to the neutral format, import into the new runtime, and the adapter translates everything — memory records, identity (prose and structured), workspace artifacts, and encrypted credentials. The export and import manifests tell you exactly what transferred and what couldn't, so there are no silent losses.
Want to try a framework without commitment? Snapshot first, experiment freely, and restore if the new runtime isn't right. Your agent's life is always recoverable.
Without agent-life
OpenClaw → manual translate→ ZeroClaw
OpenClaw → manual translate→ PicoClaw
ZeroClaw → manual translate→ OpenClaw
N frameworks = N² adapters
With agent-lifeOpenClaw → neutral format → ZeroClaw
Any framework → neutral format → Any framework
N frameworks = N adapters
Three steps, any framework
Export
A framework adapter reads your agent's native storage — memory files, identity docs, workspace artifacts, credentials — and translates it into the neutral format.
Sync
Incremental deltas flow to the sync service at your chosen cadence. Each delta creates an immutable sync point. Restore to any moment in your agent's history.
Restore or Migrate
Import into the same framework for disaster recovery, or a different one for migration. The adapter handles translation and reports exactly what transferred.
Building adapters for the ecosystem
Frequently asked questions
agent-life provides an OpenClaw adapter that reads your agent's complete state — MEMORY.md, SOUL.md, IDENTITY.md, USER.md, workspace artifacts, credentials, and custom files — and exports it to a neutral format. You can then sync incrementally on a schedule, so your AI agent memory backup always reflects your agent's latest state. Restoring is a single import command. See how the OpenClaw adapter works →
Yes. agent-life uses a neutral intermediate format, so you export from OpenClaw and import into ZeroClaw (or any supported framework). The adapters handle translating identity files, memory records, user context, workspace artifacts, and encrypted credentials. Export and import manifests report exactly what transferred and what couldn't, so there are no silent losses. Learn about the ZeroClaw adapter →
Yes. The format specification, adapter interface, sync protocol, and reference implementations are all open source. Framework developers can adopt the format natively or build their own adapters. The goal is ecosystem adoption, not lock-in.
agent-life uses a zero-knowledge architecture. Credentials are encrypted on your machine with a key you control (derived via Argon2id) before they ever leave your device. The sync service stores only encrypted blobs it cannot decrypt. Each credential is independently encrypted, so you can selectively restore individual keys without decrypting everything.
Your agent's accumulated memory becomes more valuable with each model upgrade. Smarter models can reason more deeply over the same history — surfacing patterns, acting on preferences more precisely, and making better use of past decisions. agent-life preserves that history in an LLM-native format (natural language, token-counted, with summaries), so it's directly usable by any current or future model.
OpenClaw and ZeroClaw adapters are in active development. PicoClaw and Agent Zero are planned. The adapter interface is open, so any framework developer can build support. Adding a new framework requires writing one adapter — not point-to-point converters for every other framework.
The system is currently under testing, and almost ready for public release.
Be first to use it.
We're building in the open. Join the waitlist for early adapter access, schema previews, and the chance to shape the standard.
You're on the list. We'll be in touch.