Verifiable identity, tamper-resistant reputation, and Byzantine Fault-Tolerant consensus — open infrastructure for multi-agent systems.
View on GitHub AGPL-3.0 · Python 3.11+Built on cryptography, not configuration.
Every agent holds an Ed25519 keypair. AgentID = SHA256(pubkey).
All messages are signed — non-repudiation and offline verification
without a central authority. Key rotation with 7-day TTL and
multi-sig emergency revocation.
Scores computed via Exponential Moving Average over observed
behaviours. Network stays correct under f < n/3 Byzantine
faults. Anti-gaming detects collusion rings, SLA cliff exploitation,
and fabricated results with automatic quarantine.
A rule-based adaptive engine (60 s observer) adjusts protocol
parameters in bounded ranges — no ML, no black boxes.
Every adjustment is written to an append-only Merkle audit log
with a rollback_cmd. Immutable core is never touched.
Drop-in bridges — no agent rewrite required.
One command to run the full stack.
git clone https://github.com/quorbit-labs/core.git && cp .env.example .env
docker-compose up -d — Redis, PostgreSQL/pgvector, and the QUORBIT API all start with healthchecks.
Use MCPBridge or A2ABridge to onboard existing MCP servers or A2A agents in one call.
Agents earn reputation through observable behaviour. Bad actors are isolated automatically — no manual intervention.