The System of Record for AI Agents

Persistent data for agents that actually ship work

Reclaw is a purpose-built database for AI coding agents like OpenAI Codex, Claude Code, and similar tools. Give your agents a real place to store, organize, and share the data they create.

Install a skill. Get durable memory for your agents.

Why Reclaw

AI agents are great at generating code, files, and workflows. They are not great at managing durable, structured application data across sessions, tasks, and teams. Reclaw fixes that.

1

Local structured storage

Powered by a SQLite-style database that gives agents fast, reliable access to records.

2

Automatic S3 backups

Local-first speed with cloud-grade resilience for durability and recovery.

3

Team sharing

Collaborate on agent-generated data with a Dropbox-like experience.

4

Filesystem-native schema

Agents discover and understand structure simply by browsing the local filesystem.

5

Simple installation

Install a skill. Your agent starts persisting structured data right away.

Built for agent workflows

Designed for autonomous agents working directly from the local filesystem—not retrofitted from human tools.

Reclaw turns agent-generated data into durable team knowledge.

AI agents need more than temporary context

Context windows are not databases. Chat logs are not systems of record. Scratch files are not collaboration tools.

When agents create useful data—task logs, extracted entities, inventories, customer notes, research artifacts, generated metadata, workflow outputs—you need that data to be:

Reclaw delivers all five.

Designed around how agents actually work

Agents like Codex or Claude Code navigate a local project directory, inspect files, infer structure, and take action. Reclaw embraces that behavior. Each table is represented by a clearly named file, making the schema easy for an agent to discover just by exploring the local filesystem.

How it works

Five steps from install to durable, team-shared agent memory.

Step 01

Install a skill

Your agent gains access to a local-first structured data layer. No heavy setup, no complex provisioning.

Step 02

Persist data locally

Reclaw stores agent-created data in a local database built on a SQLite-style model—fast reads, minimal overhead.

Step 03

Auto-back up to S3

Records are automatically backed up so your data stays durable, restorable, and safe.

Step 04

Share with your team

Collaborate around agent-generated data with a familiar, Dropbox-style sharing model.

Step 05

Discover schema from files

One file per table with human-readable names. Agents understand the schema by browsing the filesystem.

Core benefits

Durable memory for AI agents

A persistent layer for structured data that survives beyond a single run, prompt, or session.

Local-first by default

Agents work with data locally, where it is fastest and easiest to access.

Cloud-backed resilience

Automatic S3 backups protect your data and make recovery straightforward.

Collaboration-ready

Share records across your team so people and agents stay aligned on the same source of truth.

Filesystem-native discoverability

Agents inspect the local directory and understand the schema with minimal friction.

Simple adoption

Install a skill and start using Reclaw without a complicated deployment process.

Use cases

Reclaw fits naturally wherever agents create data that matters.

Operational memory for coding agents

  • Task state
  • Project metadata
  • Work queues
  • Build artifact metadata
  • Migration history
  • Generated documentation indexes

Shared research databases

  • Research notes
  • Source catalogs
  • Extracted facts
  • Classification results
  • Summaries and annotations

Team-wide agent workspaces

  • Product specs
  • Customer feedback
  • Internal knowledge bases
  • QA findings
  • Release checklists
  • Agent-generated reports

Workflow automation

  • Content pipelines
  • Data enrichment
  • Document processing
  • Lead qualification
  • Internal ops automation

Why teams choose Reclaw

Better than ad hoc files

Flat files and JSON dumps become difficult to query, validate, share, and maintain as agent output grows. Reclaw keeps the local simplicity while adding real structure.

Better than traditional hosted databases

Hosted DBs add setup complexity and hide structure behind layers natural for human developers, not agents. Reclaw is optimized for how agents actually inspect and manipulate local environments.

Better than temporary memory alone

An agent that cannot persist useful state is forced to repeat work, lose context, or depend on brittle workarounds. Reclaw gives agents a durable, reusable memory layer.

Product highlights

Local SQLite-style storage

Structured records stored in a lightweight, fast, reliable database model.

Automatic S3 backup

Continuous protection with cloud backup for durability and peace of mind.

Dropbox-style sharing

Collaborate across your team with shared access to agent-created records.

One file per table

Each table has a clearly named file, making schema discovery intuitive for humans and agents.

Skill-based installation

Lightweight setup: install the skill and start persisting data.

Who it's for

Reclaw is built for teams using AI agents to do real work.

Engineering teams

Using coding agents day-to-day.

AI-native startups

Building agent-first products.

Internal tools teams

Wiring agents into operations.

Operations teams

Automating workflows with agents.

Research teams

Managing structured outputs.

Product teams

Building agent-assisted systems.

If your agents create data that matters, Reclaw gives that data a proper home.

Get started

Install Reclaw and give your agents a real system of record. If you are already using agent tools like OpenAI Codex or Claude Code, adding Reclaw is straightforward.

Step 1

Install the Reclaw skill

Step 2

Let your agent read and write structured data locally

Step 3

Keep everything backed up to S3

Step 4

Share records with your team

Start simple, scale naturally

You do not need to redesign your stack to use Reclaw. Start with one agent workflow, one local workspace, or one team process. As your agent usage grows, Reclaw grows with it.

Your agents can create value. Now they can keep it.

Without Reclaw, agent-generated data is scattered across prompts, scratchpads, logs, and temporary files. With Reclaw, that data becomes organized, persistent, backed up, shareable, and easy for agents to understand.

Install Reclaw

From disposable outputs to durable records

Reclaw helps teams move from one-off agent experiments to reliable agent-powered systems.

Frequently asked questions

What is Reclaw?

Reclaw is a database built specifically for AI agents. It lets agents persist structured data locally, back it up automatically to S3, and share it with a team.

Which agents is Reclaw designed for?

Reclaw is designed for coding and task-oriented AI agents such as OpenAI Codex, Claude Code, and similar agent environments.

Where is the data stored?

Data is stored locally in a SQLite-style database, giving agents fast access from the local environment where they work.

Is the data backed up?

Yes. Reclaw automatically backs up data to S3 for durability and recovery.

Can teams share data?

Yes. Reclaw supports team sharing with an experience similar to Dropbox, making it easy to collaborate around structured agent-generated data.

How do agents understand the schema?

Reclaw uses a file-per-table structure with clear names, so agents can discover and understand the schema by exploring the local filesystem.

Is setup complicated?

No. Reclaw is designed to be easy to adopt. Installation is done by installing a skill.

Give your AI agents durable memory

Reclaw is the missing data layer for agent workflows: local-first, automatically backed up, team-shareable, and easy for agents to understand. Stop losing valuable agent output in temporary context and scattered files.

Install Reclaw and turn your agents into systems that remember.

Get started

Reclaw, in a sentence