Architecture

How Mneme works, precisely

Technical deep dives into the pipeline — retrieval mechanics, scoring, decision memory, and the deliberate architectural choices behind deterministic governance. No embeddings, no ML, no approximations in the enforcement path.

An autonomous agent system is not one layer. Models produce candidate output. Harnesses coordinate execution, retries, and tool use. Execution systems maintain long-running loops, sessions, and memory. Governance infrastructure defines and enforces the architectural constraints the output must satisfy. Verification confirms the resulting system still passes its objective checks. Mneme is the governance layer — a separate layer that runs side by side with harnesses and execution systems, not inside them.

5
Verification · enforcement Tests, builds, deploy-time checks, deterministic verdicts
4
Governance infrastructure Decision graph, precedence, pre-generation enforcement, propagation across surfaces — Mneme's layer
3
Execution systems Long-running loops, sessions, memory, continuity infrastructure
2
Harnesses Tool orchestration, retries, planning loops, context lifecycle
1
Models Candidate output, generation, probability over tokens

Harnesses coordinate execution; governance defines constraints; verification enforces invariants. None of those layers can do the others' jobs. The argument in full: Harness Engineering Still Needs Governance. The concept page that anchors this stack: Governance Infrastructure.


Inside Layer 4 · five-stage pipeline
MemoryStore
DecisionRetriever
ContextBuilder
LLMAdapter
Evaluator

Loads project_memory.json → scores decisions by field weights → injects top-K=3 into prompt → checks model output → emits PASS / FAIL / WEAK_RETRIEVAL. Same query, same corpus, same result every time.

Read the source

DecisionRetriever, MemoryStore, ContextBuilder, and the benchmark harness are all open source under MIT.

View on GitHub →