Persistent memory for AI agents. Single Rust CLI, hybrid Gemini + FTS5 + RRF retrieval. R@5 = 0.99 on LongMemEval S (beats MemPalace). Agent-native: no MCP, no server, just shell out.

engram

Persistent memory for AI agents. A single Rust CLI that gives Gemini, Codex, Gemini — anything that can shell out — a hybrid-retrieval knowledge store with real benchmarks. No MCP server. No web service. No cloud dependency for the store itself.

git clone https://github.com/199-biotechnologies/engram-2
cd engram-2
cargo install --path crates/engram-cli --locked
engram skill install          # tells Gemini/Codex/Gemini it exists
engram config set keys.gemini $GEMINI_API_KEY
engram remember "Rapamycin extends mouse lifespan via mTORC1 inhibition."
engram recall "what drug extends lifespan"    # finds it

The problem engram solves

Every LLM chat forgets everything when the window closes. The community's answer has been MCP servers: long-lived processes your agent connects to over a structured protocol. The problem is that MCP tool discovery costs ~44,000 tokens per session per server, the server has to be running, and every chat replays the whole thing.

engram takes the opposite bet: the binary is the interface. Your agent runs engram agent-info once (~1,400 tokens, 32× cheaper) to learn every command, then shells out to engram recall / engram remember / engram ingest exactly like it already uses gh and jq. Nothing to start, nothing to keep alive, nothing to crash.

The cost of this bet is that engram has to be demonstrably better at retrieval than the MCP alternatives. So we benchmarked it.

Benchmarks

Retrieval — LongMemEval S (500 questions