01
Models reason. Projects remember.
The LLM can change. The project record should not.
Back to homepage
Philosophy
The project is the brain, not the chat.
Snipara exists because coding agents are good at reasoning, but bad at owning the project record. Decisions, context, impact, and proof should survive every model, user, editor, and session.
Project Brain record
From context to proof
01 / raw context
docs, decisions, code, active work
02 / review
authority, freshness, stale warnings
03 / brief
what changed, impact, next check
04 / receipt
proof that can help the next run
Beliefs
Four rules for a useful context layer.
02
Context needs authority.
A memory without source, freshness, and review becomes noise.
03
Every brief needs a check.
A useful answer says what to verify before the work is trusted.
04
Proof survives the session.
Receipts and outcomes matter more than confident summaries.
Project Brain means the answer has a memory trail.
A coding agent can search files. Snipara's job is harder: decide which project truth is current, which context matters, what could break, and what proof closes the loop.
project-brain.json
{
"decision": "current",
"source": "reviewed memory",
"impact": ["billing", "permissions"],
"verify": ["tests", "receipt"],
"next_agent": "starts here"
}