Your AI tools forget everything. Rebis remembers.
A self-optimizing intelligence engine that runs on your hardware, compounds across every project, and cuts wasted AI token costs by eliminating redundant context. Works across every LLM. Your data never leaves your machine.
Not another memory tool
Commodity memory systems store and retrieve. Rebis is structured intelligence that activates, challenges, and compounds. Every session costs less than the last.
Structured intelligence
Not a list or vector database. Connected neurons encode how knowledge relates—when one insight is relevant, the full context fires together. Structure becomes intelligence. Your AI gets complete understanding, not isolated search results.
Learns from itself
Most AI memory only captures what works. Rebis captures what doesn't—failure modes, dead ends, and past mistakes are retained with equal weight. Your brain prevents errors before they happen by remembering what went wrong.
Blind spot detection
Independent oversight watches for over-reliance on familiar patterns, stale knowledge, and coverage gaps. Your brain actively challenges its own recommendations before they reach you—structural defense against tunnel vision and confirmation bias.
Self-optimization
Knowledge compounds through use. New insights earn trust through repeated validation. Stale knowledge fades naturally. The result is a brain that gets measurably smarter with every session—intelligence that compounds, not data that accumulates.
Watch your brain think
This is a real subgraph from a working Rebis brain. Hover neurons to explore. Click "Fire" to watch intelligence cascade through connected knowledge.
Multiple systems, not a single trick
Rebis doesn't just retrieve. Distinct layers work together so your AI tools give better answers, avoid blind spots, and get smarter with use.
Instant Recall
Your current task instantly activates the most relevant knowledge. Related neurons fire together—you get a complete picture, not isolated facts. The entire brain responds to your context in milliseconds.
Result: API Security → Privacy Controls → Memory Safety → Data Isolation
These fire as a coherent cluster, not individual lookups.
Self-Challenge
An independent layer watches for what the recall system might miss: coverage gaps, over-reliance on familiar patterns, and stale knowledge. The brain checks its own recommendations before they reach you—catching blind spots that no retrieval system would flag.
Cross-Pollination
Deliberately surfaces knowledge from unrelated domains that might apply by analogy. Generates fresh questions that challenge conventional thinking—connections you wouldn't have made yourself, drawn from the full breadth of your accumulated experience.
Signal Focus
When many neurons activate with similar relevance, competitive ranking ensures only the highest-quality recommendations reach you. No information overload—just focused, actionable intelligence. The rest is available on demand.
Continuous Growth
Every session captures what worked, what failed, and what was surprising. These traces feed back into the brain—priorities shift based on real outcomes, not just retrieval frequency. Each session makes the next one better.
Three steps to a brain that compounds
No complex setup. No configuration hell. Install, use your AI tools normally, and watch the knowledge accumulate.
Install
One command. Works with any MCP-compatible AI tool, any HTTP client, or Docker.
pip install rebis-brain
rebis init
# Local MCP (Claude Desktop/Code)
rebis mcp
# MCP Bridge (any chat interface)
rebis bridge
Your brain grows
Every session captures reasoning traces. Knowledge compounds across projects—switching tools doesn't lose the brain.
Session 1: +3 neurons (auth patterns)
Session 5: +8 neurons, connections form
Session 20: 47 neurons, graduated trust
Session 100: domain expert
AI gets smarter
Context compounds. Your AI stops asking the same questions and starts building on what it already knows.
Session 2: "What framework?"
Session 3: "What framework?"
Session 2: Applies + learns deploy
Session 3: Suggests optimizations
Brain-powered bot orchestration
Rebis doesn't just work for individual developers. It wires intelligence across entire fleets of autonomous agents—each with a sovereign brain, federated by domain expertise.
Every bot gets its own brain. The deepest expert leads.
Each agent in your fleet runs its own sovereign Rebis brain—no shared models, no merged data. When a task arrives, the bot with the deepest domain knowledge dynamically promotes to team lead, decomposes the work, and delegates sub-tasks across the fleet. Different bots can run different LLMs—Claude for reasoning, Perplexity for research, Codex for implementation—and the team lead routes work to the right brain and the right model.
- Each agent runs a sovereign brain that learns independently—no merging, no sharing
- The most domain-deep bot promotes to team lead per task and delegates work packages
- Team lead reviews all output for consistency before delivery—especially across different LLMs
- Adaptive coordination: solo execution for simple tasks, full delegation for complex ones
- Zero-trust identity between all federation members (mTLS + SPIFFE)
MCP Bridge — any interface, your data
The MCP Bridge connects Rebis to any chat interface over HTTP—not just developer tools. Claude.ai, ChatGPT, your own apps. Even if LLMs build their own memory, your data lives on their servers. With Rebis, it stays on your machine, encrypted at rest. That's the difference between renting cognition and owning it.
One brain. Every LLM. At the same time.
Rebis doesn't belong to any LLM. It works across all of them—simultaneously.
Priced for real value, not volume
A mature Rebis brain saves multiples of its cost in reduced token spend and eliminated rework. Two dimensions: human seats and agent seats. Self-hosted. No cloud bill.
- Full LOBE runtime
- All cognitive systems
- MCP + HTTP integration
- Community support
- Everything in Early Access
- Priority updates + support
- Neuron Pack marketplace
- Advanced trace analytics
- Everything in Developer
- Task delegation across team brains
- Signed envelope routing (mTLS)
- Priority support + SLA
- Everything in Team
- Dedicated architecture reviews
- Custom Neuron Packs
- SSO + compliance tooling
Agent & Bot Seats
Autonomous agents use Rebis differently—higher volume, always-on, more activation calls. Per-agent pricing or fleet packs for multi-bot orchestration.
Each autonomous agent gets a dedicated brain seat with full activation, trace capture, and self-optimization. Works with any orchestration framework.
Contact Us| Pack | Price | Per Agent | Savings |
|---|---|---|---|
| 5 agents | $159 / mo | $31.80/agent | 18% off |
| 25 agents | $599 / mo | $23.96/agent | 39% off |
| 100 agents | $1,900 / mo | $19.00/agent | 51% off |
| 250+ agents | Custom | Volume pricing | Contact us |
Connect any LLM via MCP Bridge
The MCP Bridge serves your brain over HTTP—any MCP-compatible client connects instantly. Claude.ai, ChatGPT, Perplexity, or your own apps. One command. Data stays on your machine.
pip install rebis-brain
rebis init
# Start the bridge
rebis bridge
# SSE endpoint ready at
http://localhost:7444/sse
- MCP over SSE (standard protocol)
- Optional bearer token auth
- Localhost-only by default
- All 4 cognitive tools exposed
- Claude Code / Desktop — native MCP (stdio)
- Claude.ai — via MCP Bridge
- ChatGPT — via MCP Bridge
- Perplexity — via MCP Bridge
- Custom apps — HTTP API or Bridge
- SaaS copilots — embed via Bridge
- Bot fleets — per-agent Bridge instances
The moat: Even if LLMs build their own memory, that data lives on their servers. With the MCP Bridge, your knowledge stays on your machine. Ownership, not rental.
Managed cloud hosting is on the roadmap. Interested? Let us know.
Your data is safe. Always.
Your brain data is always stored on your computer or environment—never on our servers. All graph files are encrypted at rest with a key derived from your license, so the data is unreadable without the Rebis engine. Cancel and your files stay put. Re-subscribe and the engine unlocks them right where you left off.
Start building a brain that compounds
Your AI tools will never start from zero again.