Get This Tool
RoBrain
Summary
An agent re-suggests the auth bypass you already patched, the dependency you pulled for a CVE, the migration you already rolled back — because it has no memory of why you said no. RoBrain is a shared memory layer built specifically around that failure mode.
RoBrain sits between your team's AI coding tools — Claude Code, Cursor, Copilot, Codex CLI — and a shared Postgres instance, capturing not just decisions but the alternatives your team ruled out. An MCP server runs inside the editor and surfaces relevant history before the agent acts; a batch Synthesis scan reads the whole corpus on a schedule to flag contradictions and drift that no single session would catch. That cross-session contradiction detection is where it separates from alternatives that only check at insertion time or silently delete the losing decision. Self-hosted on Apache 2.0 with your own Postgres; cloud extraction and the Planning API are paid-only features.
Bottom line: Pick this when two developers are already stepping on each other's architectural decisions across different AI tools — skip it if you're a solo developer on a project under three months old, where a well-maintained CLAUDE.md will cost you less to operate.
Hosted & API Pricing
The model is free to self-host. These are the creator's hosted/API options.Rory Plans Cloud (Early Access)
Cloud hosting with Planning API and Control MCP for automatic task-boundary injection
- Vendor-managed Postgres
- Planning API
- Control MCP
- Automatic task-boundary auto-injection
Pricing may have changed since last verified. Check the official site for current plans.
Pricing Plans
Free- Free Tier
- Self-hosted open-source mode is unlimited; no feature gates in Apache 2.0 distribution
Self-Hosted (Open-Source)
Free self-hosted mode with sensing_* tools for decision capture and injection
- Automatic decision capture via Sensing MCP
- Manual review, explain, synth, and inject via CLI
- Local Docker + Postgres storage
- Apache 2.0 license
Rory Plans Cloud (Early Access)
Cloud option available via early-access registration at roryplans.ai
- Planning API and Control MCP add task-boundary relevance scoring and automatic injection
- Conversation turns sent to Rory Plans hosted Perception API; extracted decisions stored on Rory infrastructure
- Vendor-managed Postgres
View full pricing on robrain.dev →
Pricing may have changed since last verified. Check the official site for current plans.
Community Performance Report Card
No community ratings yet. Be the first to rate this tool!
Community Benchmarks Community
Sign in to submit a benchmarkNo community benchmarks yet. Be the first to share a real-world data point.
Pros
Sign in to edit- Stores rejected alternatives as a structured field alongside each decision, so the agent surfaces why an approach was ruled out — not just what was chosen — before it re-proposes something your team already vetoed.
- Cross-session Synthesis scan reads the entire decision corpus on a schedule, so contradictions that accumulate across weeks and multiple developers get flagged rather than sitting invisible until they cause a revert.
- Old and new decisions both stay queryable when your team changes course, so reconstructing why a reversal happened is a query, not a memory exercise — unlike tools that silently replace the losing decision.
- One shared Postgres for the whole team works across Claude Code, Cursor, Copilot, and Codex CLI simultaneously, so a decision made in one editor is visible to an agent running in another without manual sync.
- Apache 2.0 self-hosted path keeps decision history on infrastructure you control, so teams with data residency requirements or cost sensitivity on API calls can run the full open-source layer without a cloud dependency.
Cons
Sign in to edit- The automatic pre-action warning — surfacing veto context before an agent makes an unsafe suggestion — is a cloud-only feature; self-hosted teams trigger inject queries manually via the CLI, which means the protection only fires when a developer remembers to ask for it, not automatically at the moment of risk.
- Synthesis runs as a scheduled batch scan, not in real time; a contradiction introduced between scans will not be flagged until the next run, so teams moving fast in a single day can still ship a conflicting decision before the corpus-wide check catches it.
- The value scales with history depth and team size — the vendor's own qualifier is that a project under a few months old with a single developer and one AI tool does not justify the setup cost. Teams in that situation who set this up and find the overhead exceeds the benefit tend to revert to a maintained CLAUDE.md and revisit RoBrain only when the codebase and team grow.
Community Reviews
Sign in to write a reviewNo reviews yet. Be the first to share your experience.
About
- Platforms
- Node.js 18.18+, npm/pnpm; Docker for local Postgres + Perception API; integrates with Claude Code, Cursor, Copilot, Codex CLI
- API Available
- Yes
- Self-Hosted
- Yes
- Last Updated
- 2026-06-01T04:00:47.881Z
Best For
Who it's for
- Multi-developer teams using Claude Code, Cursor, and Copilot
- Projects with 6+ months of accumulated architectural decisions and history
- Teams that need to track why decisions were made, not just what was chosen
- Organizations where periodic corpus-wide contradiction detection provides compliance value
What it does well
- Automatically capture architectural decisions and vetoed alternatives across developer sessions
- Flag when a new decision contradicts an old one to prevent repeated rejections
- Share decisions and vetoes across multiple developers using different AI coding tools
- Query six months of architectural decisions and ruled-out alternatives as structured data
- Surface 'don't do that again' context before unsafe or architecturally incompatible choices ship
Integrations
Discussion Community
Sign in to commentNo discussion yet. Sign in to start the conversation.
Compare RoBrain
Spotted incorrect or missing data? Join our community of contributors.
Sign Up to ContributeCommunity Notes & Tips Community
Sign in to contributeBe the first to contribute. General notes, observations, gotchas, and tips from people who use this tool day-to-day.
Frequently Asked Questions
- Is RoBrain free?
- RoBrain is a paid tool. No permanent free tier is offered.
- Is RoBrain open source?
- Yes. RoBrain is open source — the source repository is at https://github.com/adelinamart/robrain.
- Does RoBrain have an API?
- Yes. RoBrain exposes a developer API. See the official documentation at https://robrain.dev for details.
- Can I self-host RoBrain?
- Yes. RoBrain supports self-hosting on your own infrastructure.
- When was RoBrain released?
- RoBrain was first released in 2026.
- What platforms does RoBrain support?
- RoBrain is available on: Node.js 18.18+, npm/pnpm; Docker for local Postgres + Perception API; integrates with Claude Code, Cursor, Copilot, Codex CLI.
Hours Saved & ROI Stories Community
Sign in to contributeBe the first to contribute. Concrete time/cost savings, with context. e.g. "Cut my code review backlog from 4h to 45m per week."
Curated lists that include this category
Every decision an agent makes exists in a session. The moment that session ends, the reasoning behind it — and especially the reasoning behind what was rejected — vanishes. RoBrain captures both sides: what your team chose and what it ruled out, stored as structured rows with a rejected[] field in a shared Postgres instance your whole team reads from. An MCP server runs inside supported editors and fetches a session-start summary automatically; the robrain CLI handles manual review, targeted inject queries, and exports. The core loop is passive capture during coding, then periodic Synthesis scans that read the full decision corpus to surface contradictions, entity drift, and repeated rejections before they become incidents.
The distinguishing feature is what the vendor calls structured lifecycle: decisions are not permanent vetoes, and old decisions are not silently replaced when your team changes course. When a previously rejected approach becomes valid again, you supersede the old row — both the original rejection and the new active decision stay queryable. This matters for teams that need to reconstruct why a reversal happened, not just that it did. For comparison, the docs note that Claude Code Auto-Memory can flag contradictions but deletes the losing decision silently; RoBrain keeps both sides so revisiting a reversal is intentional rather than accidental.
RoBrain fits teams where more than one developer is working on the same codebase with more than one AI tool, on a project old enough that architectural contradictions have actually had time to accumulate — the vendor suggests a few months as the threshold where the memory layer starts earning its keep. Below that, a static CLAUDE.md is a reasonable alternative and the vendor says so directly. The Synthesis scan and the cloud warning layer (which surfaces veto context before an agent makes an unsafe suggestion) are where the value concentrates; teams on the self-hosted path trigger inject queries manually for pre-action context, while the cloud tier handles that injection automatically.
Integration surface is an MCP server for editor-side sensing, a CLI for review and export, and a shared Postgres you provision and own. The open-source core is Apache 2.0; the hosted extraction pipeline and Planning API are cloud-only, paid-access features not yet at published pricing.