Question 1

What is Dhee?

Accepted Answer

Dhee is an agent memory runtime. It stores useful user, project, repo, scene, and handoff memory, then compiles compact context before the next action.

Question 2

How does Dhee improve an existing agent?

Accepted Answer

Dhee adds a simple loop: compact context before the run, a dhee_memory tool during the run, and checkpoints after the run.

Question 3

How is Dhee different from Mem0, Letta, MemPalace, and agentmemory?

Accepted Answer

Dhee is the only agent memory layer that leads LongMemEval at R@5 99.4% on the full 500-question set, self-evolves its retrieval policy per tool and per intent, and ships a context router that digests Read, Bash, and subagent output at source instead of dumping raw output into context.

Question 4

Does Dhee work with ElevenLabs, Gemini, OpenAI, Codex, or MCP clients?

Accepted Answer

Yes. Dhee has native provider helpers for ElevenLabs voice agents, Gemini API agents, and OpenAI Responses agents, plus MCP, Python SDK, HTTP sidecar, CLI, and Docker surfaces.

Question 5

Is Dhee production-ready? What storage does it use?

Accepted Answer

Dhee runs on SQLite by default and can use local or hosted providers for embeddings, reranking, and rollups. Deterministic filters still run first: secrets, private scenes, contradictions, supersession, and proof gates.

Question 6

How does Dhee's self-evolution actually work?

Accepted Answer

Every time the model calls dhee_expand_result(ptr) to see the raw output behind a digest, Dhee logs the tool, intent, and depth. The command dhee router tune reads that ledger and atomically rewrites ~/.dhee/router_policy.json — deeper digests for file types the model keeps expanding, shallower ones it never does. No config to hand-maintain.