Every session you start with Claude is a blank slate. You re-explain your stack, your decisions, your conventions — every time. DepthFusion ends that. Persistent, structured memory across every session, forever.
You've spent weeks developing your architecture, making decisions, establishing patterns. Then Claude's context compacts — and it's all gone.
Stack, conventions, past decisions, ongoing work. Burned tokens before you even start. The average developer re-types 300–500 tokens of context per session.
Without memory, Claude fills your context with re-established facts instead of actual work. You're paying for repetition, not progress.
Suggest Redis one session, Postgres the next. Without memory, every answer is context-local — there's no way for Claude to know it's reversing a decision you already made.
Hit the token limit and Claude forgets the last 3 hours of architectural context. You're back to square one, re-loading mental model into the prompt manually.
Same question. Same developer. Two very different experiences.
Step through three real scenarios. Left panel shows what you and Claude experience — right panel shows the technical pipeline firing in sync.
Every token in your context window either moves your project forward or wastes money re-establishing facts. DepthFusion surfaces only what's relevant — pre-scored, pre-filtered, pre-deduplicated.
Without DepthFusion, sessions are isolated islands. With it, every session builds on the last — decisions connect to outcomes, incidents link to fixes, facts reinforce each other.
Seven typed memory objects, eight scoring dimensions, autonomous consolidation, and contradiction detection — all working silently in the background.
BM25 keyword match feeds into Haiku reranking for semantic scoring. Best-of-both precision without embedding infra overhead.
8-dimensional weighted scoring: recency, relevance, confidence, frequency, uniqueness, coherence, actionability, and source trust.
When context fills, the compressor extracts decisions, open tasks, and code references — then writes them to the store as typed memory entries.
Query patterns, decisions, and code references across all your registered projects. Knowledge doesn't silo — it flows where you need it.
Detects when new memories conflict with established facts. Flags contradictions before they reach Claude's context — your architecture stays consistent.
Every recall, publish, and feedback event is logged. Graph traversal lets you follow memory chains — discover how a decision influenced downstream work.
"Instead of spending the first 10 minutes of every session re-loading context, Claude already knows where we left off — the architecture, the decisions, the gotchas. It's like the difference between a contractor who reads the brief and one who was there from day one."
The experience of working with DepthFusion active, across a multi-week engineering project.
DepthFusion hooks into Claude Code's lifecycle events. You don't change how you work — it just starts remembering.
PostCompact and Stop hooks automatically extract decisions, patterns, and facts from every session. The LLM extractor achieves ≥80% precision — not noisy, not lossy.
The CognitiveScorer ranks every memory block across 8 dimensions. The ContradictionEngine suppresses conflicting facts. Only relevant, accurate context reaches Claude.
At the start of each session, DepthFusion runs hybrid BM25 + Haiku recall and injects the top-K scored blocks. Claude starts every session already up to speed.
When you open a new session, DepthFusion scans your knowledge graph, scores candidates, and surfaces the right memories — all in under 1.5 seconds.
DepthFusion is open source and community-driven. Ask questions, share discoveries, and help shape what gets built next.
Chat with the team and other users. Get help, share use cases, show off your setup.
Feature requests, architecture discussions, and longer-form feedback — all in the open.
Star the repo, open issues, and contribute. MIT licensed — PRs welcome.
Full reference for all 35 MCP tools, configuration profiles, and deployment guides.
One MCP server. Zero cloud dependencies. Works with every Claude Code session from the moment you install it.