--- title: "OB1 Agent Memory for OpenClaw: Reference Links" type: "guide" label: "Guide" project: "OpenClaw Crossed The Runtime Line" --- # OB1 Agent Memory for OpenClaw: Reference Links ## title: "OB1 Agent Memory for OpenClaw: Reference Links" type: "guide" label: "Guide" project: "OpenClaw Crossed The Runtime Line" # OB1 Agent Memory for OpenClaw: Reference Links This is a reference index for the OB1/OpenBrain Agent Memory release. It is not the full implementation guide. The full guide, contracts, examples, plugin package, skill, and supporting assets live in the OB1 repo and on ClawHub. ## Start Here - [OB1 GitHub repo](https://github.com/NateBJones-Projects/OB1) - [Official ClawHub package listing](https://clawhub.ai/plugins/@natebjones/ob1-agent-memory) - [OpenClaw Agent Memory recipe](https://github.com/NateBJones-Projects/OB1/tree/main/recipes/openclaw-agent-memory) - [OpenClaw integration package](https://github.com/NateBJones-Projects/OB1/tree/main/integrations/openclaw-agent-memory) - [OpenClaw native plugin source](https://github.com/NateBJones-Projects/OB1/tree/main/integrations/openclaw-agent-memory/plugin) - [OpenClaw Agent Memory skill](https://github.com/NateBJones-Projects/OB1/tree/main/skills/openclaw-agent-memory) - [![](https://substack.com/favicon.ico)Nate's Substack](https://substack.com/@natesnewsletter) - [NateBJones.com](https://natebjones.com/) ## What This Release Includes OB1 Agent Memory gives OpenClaw workflows a governed memory layer: - Recall relevant context before meaningful work starts. - Write back compact operational memory after work finishes. - Preserve source, model, runtime, task, confidence, scope, and confirmation metadata. - Keep inferred/generated memory as evidence until a human confirms it. - Give builders recipes for code review, TaskFlow handoffs, and provenance-aware memory. ## Core Recipe - [Recipe README](https://github.com/NateBJones-Projects/OB1/blob/main/recipes/openclaw-agent-memory/README.md) The main implementation guide for using OpenBrain/OB1 as a durable memory layer for OpenClaw workflows. - [Recipe metadata](https://github.com/NateBJones-Projects/OB1/blob/main/recipes/openclaw-agent-memory/metadata.json) Machine-readable package metadata for the recipe. ## Contracts - [Recall request schema](https://github.com/NateBJones-Projects/OB1/blob/main/recipes/openclaw-agent-memory/contracts/recall.schema.json) Defines what an OpenClaw workflow sends to OB1 before starting work. - [Recall response schema](https://github.com/NateBJones-Projects/OB1/blob/main/recipes/openclaw-agent-memory/contracts/recall-response.schema.json) Defines how OB1 returns scoped memories, provenance, freshness, and use policy. - [Write-back schema](https://github.com/NateBJones-Projects/OB1/blob/main/recipes/openclaw-agent-memory/contracts/writeback.schema.json) Defines how OpenClaw writes back decisions, outputs, lessons, unresolved questions, artifacts, and metadata. ## Example Payloads - [Example recall request](https://github.com/NateBJones-Projects/OB1/blob/main/recipes/openclaw-agent-memory/examples/recall-request.json) - [Example write-back request](https://github.com/NateBJones-Projects/OB1/blob/main/recipes/openclaw-agent-memory/examples/writeback-request.json) - [Example usage report](https://github.com/NateBJones-Projects/OB1/blob/main/recipes/openclaw-agent-memory/examples/usage-report.json) ## Companion Recipes - [Code Review Memory recipe](https://github.com/NateBJones-Projects/OB1/blob/main/recipes/openclaw-code-review-memory/README.md) Stores reusable repo lessons from PR reviews: conventions, recurring bugs, risky files, tests, maintainer preferences, and false positives. - [Code Review recall example](https://github.com/NateBJones-Projects/OB1/blob/main/recipes/openclaw-code-review-memory/examples/recall.json) - [Code Review write-back example](https://github.com/NateBJones-Projects/OB1/blob/main/recipes/openclaw-code-review-memory/examples/writeback.json) - [TaskFlow Work Log recipe](https://github.com/NateBJones-Projects/OB1/blob/main/recipes/openclaw-taskflow-work-log/README.md) Lets long-running OpenClaw work leave behind compact handoff memory: what was attempted, what changed, what failed, blockers, and next-agent context. - [TaskFlow recall example](https://github.com/NateBJones-Projects/OB1/blob/main/recipes/openclaw-taskflow-work-log/examples/recall.json) - [TaskFlow write-back example](https://github.com/NateBJones-Projects/OB1/blob/main/recipes/openclaw-taskflow-work-log/examples/writeback.json) ## Trust, Safety, And Provenance - [Safe Agent Memory and Provenance guide](https://github.com/NateBJones-Projects/OB1/blob/main/docs/safe-agent-memory-provenance.md) Explains why inferred/generated memory should not silently become instruction, and how OB1 handles confirmation, evidence, stale memory, disputed memory, and trusted imports. - [Agent Memory portability notes](https://github.com/NateBJones-Projects/OB1/blob/main/docs/agent-memory-portability.md) Notes on keeping OB1 Agent Memory runtime-neutral instead of over-coupled to OpenClaw. ## Database Schema - [Agent Memory schema README](https://github.com/NateBJones-Projects/OB1/blob/main/schemas/agent-memory/README.md) Overview of the database model for governed agent memory. - [Agent Memory SQL schema](https://github.com/NateBJones-Projects/OB1/blob/main/schemas/agent-memory/schema.sql) Sidecar schema for memory records, provenance, use policy, review state, source references, recall traces, trace items, relations, and audit events. ## Runtime-Neutral API - [Agent Memory API integration](https://github.com/NateBJones-Projects/OB1/tree/main/integrations/agent-memory-api) Runtime-neutral API surface for recall, write-back, usage reporting, review actions, inspector reads, recall traces, and health checks. - [API README](https://github.com/NateBJones-Projects/OB1/blob/main/integrations/agent-memory-api/README.md) - [API implementation](https://github.com/NateBJones-Projects/OB1/blob/main/integrations/agent-memory-api/index.ts) - [Live smoke test](https://github.com/NateBJones-Projects/OB1/blob/main/integrations/agent-memory-api/smoke/live-smoke.mjs) - [Demo seed script](https://github.com/NateBJones-Projects/OB1/blob/main/integrations/agent-memory-api/smoke/seed-nate-continuity-demo.mjs) ## OpenClaw Plugin - [OpenClaw integration folder](https://github.com/NateBJones-Projects/OB1/tree/main/integrations/openclaw-agent-memory) Contains the native OpenClaw plugin package, publishing notes, release notes, and plugin skill bundle. - [Integration README](https://github.com/NateBJones-Projects/OB1/blob/main/integrations/openclaw-agent-memory/README.md) - [ClawHub publishing notes](https://github.com/NateBJones-Projects/OB1/blob/main/integrations/openclaw-agent-memory/CLAW_HUB_PUBLISHING.md) - [Plugin README](https://github.com/NateBJones-Projects/OB1/blob/main/integrations/openclaw-agent-memory/plugin/README.md) - [Plugin manifest](https://github.com/NateBJones-Projects/OB1/blob/main/integrations/openclaw-agent-memory/plugin/openclaw.plugin.json) - [Plugin package.json](https://github.com/NateBJones-Projects/OB1/blob/main/integrations/openclaw-agent-memory/plugin/package.json) - [Plugin source](https://github.com/NateBJones-Projects/OB1/tree/main/integrations/openclaw-agent-memory/plugin/src) - [Native OpenClaw smoke test](https://github.com/NateBJones-Projects/OB1/blob/main/integrations/openclaw-agent-memory/plugin/smoke/native-openclaw-smoke.sh) ## OpenClaw Skill - [Skill README](https://github.com/NateBJones-Projects/OB1/blob/main/skills/openclaw-agent-memory/README.md) - [Skill instructions](https://github.com/NateBJones-Projects/OB1/blob/main/skills/openclaw-agent-memory/SKILL.md) - [Skill metadata](https://github.com/NateBJones-Projects/OB1/blob/main/skills/openclaw-agent-memory/metadata.json) The skill tells OpenClaw agents how to behave around memory: recall before meaningful work, write back compact operational memory, avoid raw transcript dumps, preserve provenance, and never treat inferred memory as confirmed instruction. ## Visual Assets - [Agent Memory visual asset index](https://github.com/NateBJones-Projects/OB1/blob/main/docs/assets/agent-memory/README.md) - [Diagram source files](https://github.com/NateBJones-Projects/OB1/tree/main/docs/assets/agent-memory) - [Exported SVG diagrams](https://github.com/NateBJones-Projects/OB1/tree/main/docs/assets/agent-memory/exports) - [Video-ready PNG diagrams](https://github.com/NateBJones-Projects/OB1/tree/main/docs/assets/agent-memory/video) - [Dashboard screenshots](https://github.com/NateBJones-Projects/OB1/tree/main/docs/assets/agent-memory/screenshots) - [Promotional assets](https://github.com/NateBJones-Projects/OB1/tree/main/docs/assets/agent-memory/promotional) - [OB1/NBJ brand assets](https://github.com/NateBJones-Projects/OB1/tree/main/docs/assets/agent-memory/brand) ## Dashboard Walkthrough Assets - [Dashboard walkthrough folder](https://github.com/NateBJones-Projects/OB1/tree/main/docs/walkthroughs/ob1-agent-dashboard) - [Walkthrough README](https://github.com/NateBJones-Projects/OB1/blob/main/docs/walkthroughs/ob1-agent-dashboard/README.md) This folder contains the screenshot capture scripts, demo seed data, guide generation scripts, and Remotion-based video walkthrough source for the OB1 Agent Dashboard. ## Release Notes - [OpenClaw Agent Memory v0.1.0 release notes](https://github.com/NateBJones-Projects/OB1/blob/main/integrations/openclaw-agent-memory/RELEASE_NOTES_0.1.0.md) - [OpenClaw Agent Memory v0.1.1 release notes](https://github.com/NateBJones-Projects/OB1/blob/main/integrations/openclaw-agent-memory/RELEASE_NOTES_0.1.1.md) ## Suggested Reader Path 1. Start with Nate’s Substack article for the strategy and framing. 2. Use the [OpenClaw Agent Memory recipe](https://github.com/NateBJones-Projects/OB1/blob/main/recipes/openclaw-agent-memory/README.md) for the implementation pattern. 3. Review the [recall](https://github.com/NateBJones-Projects/OB1/blob/main/recipes/openclaw-agent-memory/contracts/recall.schema.json) and [write-back](https://github.com/NateBJones-Projects/OB1/blob/main/recipes/openclaw-agent-memory/contracts/writeback.schema.json) contracts. 4. Install or inspect the [official ClawHub package](https://clawhub.ai/plugins/@natebjones/ob1-agent-memory). 5. Use the companion recipes for concrete workflows: - [Code Review Memory](https://github.com/NateBJones-Projects/OB1/blob/main/recipes/openclaw-code-review-memory/README.md) - [TaskFlow Work Log](https://github.com/NateBJones-Projects/OB1/blob/main/recipes/openclaw-taskflow-work-log/README.md) 6. Read the [Safe Agent Memory and Provenance guide](https://github.com/NateBJones-Projects/OB1/blob/main/docs/safe-agent-memory-provenance.md) before allowing agent-written memory to become instruction-grade.