海马记忆系统

Auto-installed claude-code hook in CLAUDE.md

```

If you have a CLAUDE.md, it patches it. AGENTS.md for Codex/OpenClaw/OpenCode. .cursorrules for Cursor. For Codex, Hippo also wraps the detected launcher in place so /exit can consolidate memory without a manual PATH step. No manual hook install needed. Your agent starts using Hippo on its next session.

It also registers the current project in Hippo's workspace registry and installs one machine-level daily runner (6:15am). That runner sweeps every registered workspace, runs hippo learn --git --days 1, then hippo sleep. You get strict daily consolidation without creating one OS task per project.

To skip: hippo init --no-hooks --no-schedule

---

Output: "Previously observed (2026-03-10): deploy takes ~3 min"

hippo context --framing suggest

Output: "Consider: deploy takes ~3 min"

hippo context --framing assert

Output: "Deploy takes ~3 min"

```

Three modes: observe (default), suggest, assert. Choose based on how directive you want the memory to be.

---

next time an agent asks about build issues, the memory is there

```

---

Auto-install (recommended)

hippo init detects your agent framework and patches the right config file automatically:

No extra commands needed. Just hippo init and your agent knows about Hippo.

Manual install

If you prefer explicit control:

hippo hook install claude-code   # patches CLAUDE.md + adds SessionStart/SessionEnd + UserPromptSubmit hooks
hippo hook install codex         # optional repair/manual run: patches AGENTS.md + wraps the detected Codex launcher
hippo hook install cursor        # patches .cursorrules
hippo hook install openclaw      # patches AGENTS.md
hippo hook install opencode      # patches AGENTS.md + installs the opencode TS plugin

This adds a ` ... ` block that tells the agent to: 1. Run hippo context --auto --budget 1500 at session start 2. Run hippo remember "<lesson>" --error on errors 3. Run hippo outcome --good on completion

For Claude Code, it also adds: - a SessionEnd hook so hippo sleep runs automatically when the session exits - a SessionStart hook that prints the previous session's consolidation output - a UserPromptSubmit hook that runs hippo context --pinned-only --include-recent 5 --format additional-context every turn. It re-injects pinned memories (hippo remember <text> --pin) plus the last 5 writes, so fresh same-session lessons appear on the next prompt before you pin them. Opt out with {"pinnedInject":{"enabled":false}} in .hippo/config.json.

To remove: hippo hook uninstall claude-code

Quick start

```bash npm install -g hippo-memory

Manual usage

hippo remember "FRED cache silently dropped the tips_10y series" --tag error hippo recall "data pipeline issues" --budget 2000 ```

---

Full release history: CHANGELOG.md · GitHub Releases

What the hook adds (Claude Code example)

```markdown

Zero-config agent integration

hippo init auto-detects your agent framework and wires itself in:

```bash cd my-project hippo init

Invalidated 5 memories referencing "REST API".

```

---

CLI Reference

---

BM25: matched [data, pipeline]; cosine: 0.82

Framework Integrations

OpenClaw Plugin

Native plugin with auto-context injection, workspace-aware memory lookup, and tool hooks for auto-learn / auto-sleep. When autoSleep is enabled, the OpenClaw plugin now launches hippo sleep in a detached background worker at session end so the live session can exit immediately.

Query-time retrieval still uses the active workspace store plus the shared global store. Daily consolidation comes from the machine-level runner that hippo init / hippo setup installs.

openclaw plugins install hippo-memory
openclaw plugins enable hippo-memory

Plugin docs: extensions/openclaw-plugin/. Integration guide: integrations/openclaw.md.

Claude Code Plugin

Plugin with SessionStart/Stop hooks and error auto-capture. See extensions/claude-code-plugin/.

Full integration details: integrations/

---

Comparison

The AI-memory category matured fast in 2026. Hippo's specific take — bio-decay, strengthen-on-use, outcome-weighted half-lives — is one stance among several. The table below is a feature snapshot, not a verdict: graph-first systems (gbrain, Zep, Cognee), agent-managed systems (Letta), and version-control / skill-distillation takes (Memoria, EverMind) all solve adjacent problems with different mechanics.

\* Split-mismatched: Hippo's 86.8% is on longmemeval_oracle (3 sessions per haystack); gbrain's 97.6% is on longmemeval_s_cleaned (~40 sessions per haystack). Different splits, different difficulty. Not directly comparable.

\\ Different metric: Memoria's 88.78% and EverMind's 83% are reported as overall accuracy with a reader LLM, not retrieval R@5. Higher denominator + LLM helps. Not directly comparable to retrieval-only R@5 numbers above.

Different tools answer different questions. Mem0 and Basic Memory implement "save everything, search later." MemPalace implements "store everything, organize spatially for retrieval." gbrain, Zep, and Cognee implement "extract typed entities and relationships into a knowledge graph." Letta implements "the agent edits its own memory blocks." Memoria implements "Git-style version control over the memory state itself." EverMind implements "self-evolving Skill Memory + multi-modal retrieval over hierarchical scopes." Hippo implements "forget by default, earn persistence through use." These are complementary takes, not a single-axis ranking: bio-lifecycle (Hippo) + GraphRAG (gbrain/Cognee/Zep) + agent-self-edit (Letta) + memory-VCS (Memoria) + skill-distillation (EverMind) cover different parts of the same problem.

---