Not lost in chat.
Decision memory for AI-assisted projects and backend services — every choice stored with rationale, linked by dependencies, versioned, and available through REST or MCP.
Let’s not use Redis. LRU in-memory, 5-min TTL. We don’t need the complexity.
Agreed. LRU with Map-based approach, 5-min TTL.
· · · 130 lines later · · ·
Setting up Redis with ioredis and a connection pool▎
This happens every session. Every context switch. Every new chat.
Decision graph
Internal engine extracts relationships and assigns confidence weights to every edge. The graph returns not just what depends on a decision, but how strongly.
Change a decision — the agent sees ranked downstream impact before a single line of code moves.
What changes
The agent works inside the lines your team already set. Decisions, assumptions, constraints — one system.
Blast radius with weighted dependencies — exact list of affected entities, severity, depth. One second.
Agent opens a fresh session and instantly knows every decision, constraint, and where you left off.
Every assumption carries invalidation triggers. When the world changes, the system flags it.
You write decisions. AI enrichment finds relationships — dependencies, derivations, potential tensions. Automatically.
Built-in onboarding extracts decisions from your codebase, configs, and git history. Works on day one.
In practice
Team of 6 + 3 AI agents, 14 months in prod
“Migrating to GraphQL? 89 entities affected. We saw the blast radius before writing a single resolver.”
2 founders, AI-first, 47 regulatory constraints
“Regulator changed KYC rules. "What depends on identity verification?" — 142 entities, 12 critical. Scoped in minutes.”
Solo founder with Cursor + Claude Code
“One tech stack decision affected 86% of the project. One assumption had 185 decisions depending on it.”
Who is this for
You don’t remember all the dependencies anymore. Your agent remembers even less. Graven holds the map — so neither of you has to.
Everyone makes decisions that affect others. Without the dependency graph, conflicts surface on production. With it — they surface before code.
100 messages is enough for an agent to forget a decision from the start. After 3 sessions — it doesn’t exist. After 10 — the team re-makes it from scratch.
Pricing
Starter
$9.99/mo
For solo builders getting started.
14-day free trial
Solo
$50/mo
Full power for solo developers.
Pro
$200/mo
For teams and complex projects.
Enterprise
Custom
Custom limits, SSO, dedicated support.