Documentation

Build on Bilinc without leaving Bilinc.

Install the cloud-only SDK, understand the hosted memory lifecycle, and move into Python, MCP, and operator workflows from one first-party docs surface.

Install pathPyPI package
RuntimeHosted Bilinc Cloud
InterfacePython + CLI + MCP
AccessBILINC_API_KEY
Overview

Bilinc is a verifiable memory and state plane for autonomous agents.

It combines typed memory, belief revision, verification, audit trail, and recovery primitives so long-running agents can preserve durable state instead of only storing vectors.

Memory model

Working, episodic, procedural, semantic, and spatial memory.

Integrity

Z3 verification, AGM revision, and Merkle audit history.

Recovery

Snapshots, diffs, and rollback for bounded incident response.

State lifecycle

Four moves cover most agent-memory work.

Commit

Write a memory with type and importance through the hosted API.

Recall

Query hosted memory with fast, balanced, verified, or deep profiles.

Operate

Use hosted retention, audit, and entitlement gates instead of local runtime internals.

Upgrade

Move from trial to Pro, Team, Scale, or Enterprise as usage grows.

Recall model

Choose the retrieval posture, not just the query.

Bilinc fuses lexical, vector, and graph signals inside the hosted state plane. Current `main` also includes evidence-aware recall helpers such as claim projection, contradiction probes, and named recall profiles.

fast

Latency-first hosted recall.

balanced

Default profile for most agent workflows.

verified

Adds evidence metadata for operator review.

deep

Uses the richest hosted retrieval path when quality matters most.

Next

Go deeper by task.