Build System
The Synix build system is an open-source pipeline for declarative agent memory.
Status: Shipped. Python, MIT license, 10 releases.
What it does
Section titled “What it does”Define memory architecture as a DAG of sources, transforms, and projections. Change a rule, rebuild incrementally. Every artifact is content-addressed with full provenance — you can trace any output back to its sources through SHA256 lineage chains.
Core capabilities:
- Declarative pipeline definitions with DAG execution
- Content-addressed artifact storage with provenance tracking
- Incremental rebuilds (changed layers rebuild, unchanged cache)
- Hybrid search: keyword (FTS5), semantic, and layered
- Generic LLM transforms: MapSynthesis, GroupSynthesis, ReduceSynthesis, FoldSynthesis
- Validation: mutual exclusion, required fields, PII detection, semantic conflict checking
- MCP server for agent consumption
- Execution memory protocol (stack+heap model) — 65% token reduction on GPT-5.2
What it demonstrated
Section titled “What it demonstrated”Treating memory as an engineering problem — with versioning, provenance, and lifecycle management — produces better outcomes than flat storage. The build system is essentially MapReduce for memory: repeatable, auditable, diffable.
What it does not do
Section titled “What it does not do”The build system operates on cold data — conversations and documents that have already been generated. A batch pipeline running every 60 seconds with a 300-second cooldown cannot manage real-time state, coordinate multiple agents, or react to events as they happen.
This limitation motivated the memory architecture.
Documentation
Section titled “Documentation”Full documentation is maintained in the Synix repository: