docs / agent-knowledge / overview

agent-knowledge

Shared knowledge for multi-agent spaces — signed claims with pedigree.

fg-agent-knowledge standardizes what a team of agents knows, as distinct from what any single agent remembers. Per-agent memory is deliberately out of scope (that belongs to the agent's harness — see agent-memory); this library is the unowned layer between agents: the claims a space holds, who asserted them, who has corroborated or contradicted them, and how much they should be trusted right now.

The core idea

Knowledge is modeled as signed claims with pedigree, governed by explicit promotion:

What is standardized — and what deliberately isn't

Standardized (the fixed core) Left open (competes)
Claim format & signing domain Storage engines (Store seam)
Trust semantics (confidence ⊥ staleness) Ranking algorithms (Retriever seam)
Governance verbs & promotion rules Consolidation intelligence (LLMs are consumers)
Wire spec & golden vectors Reputation / source weighting (SourceWeight seam)

Model-free by design: no LLM appears anywhere in the protocol. Briefings are assembled — ranked, attributed claims — never generated.

Position in the stack

First planned consumer: Zigura workspaces.

Status

Version 0.2.0 (alpha) · Python ≥ 3.11 · 100+ hermetic tests (no network, no LLM) · complete normative wire spec (spec/SPEC.md, RFC-2119) with byte-stable golden vectors. Treat it as a working reference, not a stable dependency — the wire format is not yet frozen.

→ Start with Getting started · Concepts · API reference · Examples