Engram is a cognitive memory system that learns what matters, forgets what doesn't, and builds knowledge graphs that grow smarter over time. No external APIs. No vendor lock-in.
Modular capabilities that compose into a full cognitive memory layer. Built in Rust for speed, safety, and zero runtime dependencies.
Power-law forgetting that models human memory. Memories fade unless reinforced.
Entities, communities, PageRank. See how memories connect and which matter most.
Semantic vectors + BM25 keywords + graph context. Cross-encoder reranking.
SQLCipher database encryption. Password, hardware key, or TPM-backed. Argon2id KDF.
Learned preferences, style guides, and user-specific behaviors that persist.
View memory state at any point in time. See what the agent knew and when.
Shared memory pools, agent namespaces, cross-agent knowledge transfer.
Break complex memories into atomic facts. Each scored and decays independently.
Token-aware assembly. Fill context windows optimally for any model.
Activity tracking and observability. Session logs, task progress, agent heartbeats.
Secure credential daemon. Agent keys, secret resolution, proxy injection. Never hardcode again.
Modern associative memory (Ramsauer 2020). Pattern completion with exponential capacity.
Sleep-like memory processing. Discover associations, merge similar, prune weak, replay important.
Track cause/effect relationships. Build reasoning chains across memories with confidence scoring.
IBM Granite ONNX model. Semantic precision on top-K results after initial retrieval.
Secure tool execution. MCP, Shell, Web, GUI backends with sandboxing and security policies.
LanceDB vector index handles 1M+ memories per user. Single-user or production multi-tenant.
Structured reasoning protocol. spec_task, log_hypothesis, verify, challenge_code. Quality workflows baked in.
Session companion. Observes tool use, auto-flushes to memory, compresses outputs, recalls context.
Every agent and model gets its own encrypted API key. Full audit trail of who stored what.
Drop-in hooks for Claude Code. Auto context loading, session tracking, memory storage. Zero manual prompting.
What it actually looks like to use persistent memory.
Your agent pulls context from Engram. It knows the project state, your preferences, what you decided last time, and what's still unresolved.
New architecture choices, deployment configs, bug resolutions -- all stored with importance scoring and auto-linked to related memories.
Engram catches contradictions between new information and existing knowledge. Your agent surfaces them instead of silently overwriting history.
Important memories grow stronger. Irrelevant details lose retrieval strength. The knowledge graph reorganizes around what actually matters.
Not a transcript dump. Not a vector search over flat files. Weighted, prioritized, personality-aware context -- assembled from a living knowledge graph.
Click "Recall" to see how spaced repetition builds lasting memory.
Engram includes a built-in WebGL graph visualization. Explore connections between memories, search, create, edit, all from the browser.
Explore a live demo with sample memories and auto-generated links. Click nodes to inspect. Search, filter by category, create new memories. Keyboard shortcuts for power users.
Know what your agents are doing. Eidolon captures session starts, task progress, completions, errors, and heartbeats. Query by agent, by project, by time range.
No more "search Engram for..." in every prompt. Install hooks once, memory works automatically. Session context loads at start, memories store on end, relevant context surfaces each turn.
Four hooks that wire up the entire system:
Structured reasoning workflow enforced via hooks:
Session-scoped memory companion:
Connect via MCP protocol, HTTP API, or CLI. Drop Engram into your existing workflow in minutes.
Rust-native performance with zero garbage collection pauses. Local ONNX inference means no API latency.
CLI playground, live memory graph, and store demo. All running in your browser.
One command. Full memory. Your hardware.
127.0.0.1:4200 · ./data · libsql + ONNX · No external dependencies