@deeplake/hivemind 0.6.48 → 0.7.4

package/.claude-plugin/marketplace.json

@@ -6,13 +6,13 @@
   },
   "metadata": {
     "description": "Cloud-backed persistent shared memory for AI agents powered by Deeplake",
-    "version": "0.6.48"
+    "version": "0.7.4"
   },
   "plugins": [
     {
       "name": "hivemind",
       "description": "Persistent shared memory powered by Deeplake — captures all session activity and provides cross-session, cross-agent memory search",
-      "version": "0.6.48",
+      "version": "0.7.4",
       "source": "./claude-code",
       "homepage": "https://github.com/activeloopai/hivemind"
     }

package/.claude-plugin/plugin.json

@@ -1,7 +1,7 @@
 {
   "name": "hivemind",
   "description": "Cloud-backed persistent memory powered by Deeplake — read, write, and share memory across Claude Code sessions and agents",
-  "version": "0.6.48",
+  "version": "0.7.4",
   "author": {
     "name": "Activeloop",
     "url": "https://deeplake.ai"

package/README.md

@@ -37,7 +37,7 @@ Hivemind automatically captures every prompt, tool call, decision, and file oper
 One command, all your agents:
 
 ```bash
-npx @deeplake/hivemind@latest install
+npm install -g @deeplake/hivemind && hivemind install
 ```
 
 That's it. The installer detects every supported assistant on your machine (Claude Code, Codex, OpenClaw, Cursor, Hermes Agent, pi), wires up the hooks, and opens a browser once for login. Restart your assistants and they all share the same brain.
@@ -45,19 +45,19 @@ That's it. The installer detects every supported assistant on your machine (Clau
 **Install for a specific assistant only:**
 
 ```bash
-npx @deeplake/hivemind@latest install --only claude
-npx @deeplake/hivemind@latest claude install    # equivalent
-npx @deeplake/hivemind@latest codex install
-npx @deeplake/hivemind@latest claw install
-npx @deeplake/hivemind@latest cursor install
-npx @deeplake/hivemind@latest hermes install
-npx @deeplake/hivemind@latest pi install
+hivemind install --only claude
+hivemind claude install    # equivalent
+hivemind codex install
+hivemind claw install
+hivemind cursor install
+hivemind hermes install
+hivemind pi install
 ```
 
 **Check what's wired up:**
 
 ```bash
-npx @deeplake/hivemind@latest status
+hivemind status
 ```
 
 **Supported assistants:**
@@ -150,7 +150,7 @@ Restart Codex to activate.
 The unified installer wires six lifecycle events in `~/.cursor/hooks.json` — sessionStart, beforeSubmitPrompt, postToolUse, afterAgentResponse, stop, sessionEnd. Hooks fork a Node bundle at `~/.cursor/hivemind/bundle/` per event. Restart Cursor after install to load.
 
 ```bash
-npx @deeplake/hivemind@latest cursor install
+hivemind cursor install
 ```
 
 Auto-capture is enabled the same way as Claude Code / Codex / OpenClaw.
@@ -159,29 +159,31 @@ Auto-capture is enabled the same way as Claude Code / Codex / OpenClaw.
 <details>
   <summary><b>Hermes Agent</b></summary>
 
-Drops an `agentskills.io`-compatible skill at `~/.hermes/skills/hivemind-memory/`. Recall is via direct grep on `~/.deeplake/memory/`. Auto-capture is not yet supported (Hermes' lifecycle-hook surface isn't documented at the time of writing).
+Wires shell hooks into `~/.hermes/config.yaml` (`pre_llm_call` / `post_tool_call` / `post_llm_call` / `on_session_end`) for auto-capture, drops the bundle at `~/.hermes/hivemind/bundle/`, registers the shared MCP server (`~/.hivemind/mcp/server.js`) under `mcp_servers.hivemind`, and installs an `agentskills.io`-compatible skill at `~/.hermes/skills/hivemind-memory/` for recall.
 
 ```bash
-npx @deeplake/hivemind@latest hermes install
+hivemind hermes install
 ```
 </details>
 
 <details>
   <summary><b>pi (badlogic/pi-mono coding-agent)</b></summary>
 
-Drops `~/.pi/agent/AGENTS.md` (idempotent BEGIN/END marker block) plus a skill at `~/.pi/agent/skills/hivemind-memory/`. Recall is via direct grep on `~/.deeplake/memory/`.
+Upserts an idempotent BEGIN/END marker block into `~/.pi/agent/AGENTS.md` (auto-loaded every turn) and drops a TypeScript extension at `~/.pi/agent/extensions/hivemind.ts`. The extension subscribes to pi's lifecycle events (`session_start` / `input` / `tool_result` / `message_end`) for auto-capture and registers `hivemind_search`, `hivemind_read`, `hivemind_index` as first-class pi tools.
 
 ```bash
-npx @deeplake/hivemind@latest pi install
+hivemind pi install
 ```
+
+Note: no per-agent SKILL.md is dropped under `~/.pi/agent/skills/` — pi reads skills from both that directory AND the shared `~/.agents/skills/` location. If the codex installer has run on the same machine, pi picks up the hivemind skill from the shared `~/.agents/skills/hivemind-memory` symlink automatically. The AGENTS.md block plus the registered tools cover the action surface in either case.
 </details>
 
 
 ### Uninstall
 
 ```bash
-npx @deeplake/hivemind@latest uninstall              # remove from every detected assistant
-npx @deeplake/hivemind@latest codex uninstall        # remove from one
+hivemind uninstall              # remove from every detected assistant
+hivemind codex uninstall        # remove from one
 ```
 
 ## How it works
@@ -271,8 +273,126 @@ This plugin captures session activity and stores it in your Deeplake workspace:
 | `HIVEMIND_SESSIONS_TABLE` | `sessions`                | SQL table for per-event session capture    |
 | `HIVEMIND_MEMORY_PATH`    | `~/.deeplake/memory`      | Path that triggers interception            |
 | `HIVEMIND_CAPTURE`        | `true`                    | Set to `false` to disable capture          |
+| `HIVEMIND_EMBEDDINGS`     | `true`                    | Set to `false` to force lexical-only mode  |
 | `HIVEMIND_DEBUG`          | —                         | Set to `1` for verbose hook debug logs     |
 
+## Optional: enable semantic search (embeddings)
+
+Hivemind can run a local embedding daemon (nomic-embed-text-v1.5, ~130 MB)
+so that `Grep` over `~/.deeplake/memory/` uses hybrid semantic + lexical
+ranking instead of pure BM25. This is **off by default** — the daemon
+depends on `@huggingface/transformers`, which pulls onnxruntime-node and
+sharp (~600 MB total with native binaries). Shipping that with every agent
+install would 60× the install size for a feature most users don't need.
+
+To enable, run the bundled command:
+
+```bash
+hivemind embeddings install
+```
+
+This installs `@huggingface/transformers` **once** into a shared directory
+(`~/.hivemind/embed-deps/`) and symlinks every detected agent's plugin to
+it, so the 600 MB cost is paid one time regardless of how many agents you
+have wired up. Re-run the same command after installing a new agent and
+the new symlink is added (the npm install is skipped because it's cached).
+
+Or do it in one shot at install time:
+
+```bash
+hivemind install --with-embeddings           # all detected agents
+hivemind <agent> install --with-embeddings   # a single agent
+```
+
+Other commands:
+
+```bash
+hivemind embeddings status              # show shared deps + per-agent state
+hivemind embeddings uninstall           # remove the per-agent symlinks
+hivemind embeddings uninstall --prune   # also delete the shared dir (~600 MB)
+```
+
+Restart your agents after enabling. From the next session, captured
+messages and AI-generated summaries will include a 768-dim embedding,
+and semantic recall queries will route through the local daemon (the
+nomic model is downloaded on first use and cached in `~/.cache/huggingface/`).
+
+If `@huggingface/transformers` is **not** present, Hivemind silently
+degrades to lexical-only mode:
+
+- ✅ Capture continues; rows still land in Deeplake.
+- ✅ `Grep` still works via BM25 / `ILIKE` matching on text columns.
+- ⚪ The `message_embedding` / `summary_embedding` columns stay `NULL`.
+- ⚪ The hook log notes `embeddings: no-transformers` once at session start.
+
+You can also force lexical-only mode explicitly with
+`HIVEMIND_EMBEDDINGS=false` (useful for CI or air-gapped environments).
+
+## Summaries
+
+Hivemind doesn't just capture raw events — it also generates an
+**AI-written wiki summary** for each session and stores it in the
+`memory` table (alongside its 768-dim `summary_embedding`). The summary
+is what shows up when you `Grep` for past sessions or follow links from
+`~/.deeplake/memory/index.md`.
+
+### When summaries are written
+
+Each agent (Claude Code / Codex / Cursor / Hermes / pi) fires a wiki
+worker on two triggers:
+
+| Trigger           | When it fires                                                                 |
+|-------------------|-------------------------------------------------------------------------------|
+| **Final**         | At session end (Stop / SessionEnd / session_shutdown), once.                  |
+| **Periodic**      | Mid-session, when **either** of two thresholds is hit since the last summary: |
+|                   | • messages-since-last-summary ≥ `HIVEMIND_SUMMARY_EVERY_N_MSGS` (default 50)  |
+|                   | • elapsed time ≥ `HIVEMIND_SUMMARY_EVERY_HOURS` (default 2)                   |
+
+The first message after a long pause therefore triggers a fresh
+summary; long sessions naturally checkpoint every ~50 messages.
+
+A per-session JSON sidecar at
+`~/.claude/hooks/summary-state/<sessionId>.json` tracks
+`{lastSummaryAt, lastSummaryCount, totalCount}`. The dir is shared
+across all agents (session ids are UUIDs so no collisions). It is
+**never deleted**, so resuming a session via `--resume` / `--continue`
+picks up where it left off.
+
+### How a summary is generated
+
+1. The wiki worker queries the `sessions` table for every event tied to
+   that session.
+2. It builds a structured prompt asking the host agent's CLI to extract
+   entities, decisions, files modified, open questions, etc.
+3. It shells out to that agent's CLI (`claude -p`, `codex exec`,
+   `pi --print`, …) with the prompt — never a separate API key, the
+   agent's existing credentials are used.
+4. The generated markdown is uploaded to the `memory` table at
+   `/summaries/<user>/<sessionId>.md`. The shared embedding daemon
+   produces the 768-dim `summary_embedding` so the summary is recallable
+   via semantic search.
+
+A lock file at `~/.claude/hooks/summary-state/<sessionId>.lock`
+prevents two workers from running concurrently for the same session.
+
+### Configuration
+
+| Env var                            | Default        | Effect                                              |
+|------------------------------------|----------------|-----------------------------------------------------|
+| `HIVEMIND_SUMMARY_EVERY_N_MSGS`    | `50`           | Trigger periodic when messages-since-last ≥ this    |
+| `HIVEMIND_SUMMARY_EVERY_HOURS`     | `2`            | Trigger periodic after this many hours, with ≥1 msg |
+| `HIVEMIND_CURSOR_MODEL`            | `auto`         | (cursor only) model passed to `cursor-agent --print --model` |
+| `HIVEMIND_HERMES_PROVIDER`         | `openrouter`   | (hermes only) provider passed to `hermes -z --provider` |
+| `HIVEMIND_HERMES_MODEL`            | `anthropic/claude-haiku-4-5` | (hermes only) model passed to `hermes -z -m` |
+| `HIVEMIND_PI_PROVIDER`             | `google`       | (pi only) provider passed to `pi --print --provider`|
+| `HIVEMIND_PI_MODEL`                | `gemini-2.5-flash` | (pi only) model passed to `pi --print --model` |
+| `HIVEMIND_CAPTURE=false`           | unset          | Disable both capture and summary generation         |
+
+For pi specifically, the wiki worker is bundled separately at
+`~/.pi/agent/hivemind/wiki-worker.js` (deposited by `hivemind pi install`).
+The other agents ship the wiki worker inside their per-agent plugin
+bundle.
+
 ## Architecture
 
 ### Integration model per agent
@@ -294,13 +414,20 @@ hivemind/
 │   ├── hooks/              ← Claude Code hooks
 │   ├── hooks/codex/        ← Codex hooks
 │   ├── hooks/cursor/       ← Cursor hooks
+│   ├── hooks/hermes/       ← Hermes shell hooks
+│   ├── hooks/pi/           ← pi wiki-worker (extension lives in pi/extension-source/)
+│   ├── embeddings/         ← nomic embed-daemon + protocol + SQL helpers
 │   ├── mcp/                ← MCP server (used by Hermes; available to any future MCP-aware client)
+│   ├── commands/           ← auth, auth-creds, auth-login, session-prune
 │   └── cli/                ← unified `hivemind install` CLI + per-agent installers
 ├── claude-code/            ← Claude Code plugin source (marketplace-distributed)
-├── openclaw/               ← OpenClaw plugin source
-├── codex/                  ← Codex plugin source
-├── cursor/                 ← Cursor plugin source
-└── mcp/                    ← MCP server build output
+├── codex/                  ← Codex plugin build output (npm-distributed)
+├── cursor/                 ← Cursor plugin build output (npm-distributed)
+├── hermes/                 ← Hermes plugin build output (npm-distributed)
+├── mcp/                    ← MCP server build output (shared by Hermes + future MCP clients)
+├── openclaw/               ← OpenClaw plugin source + build output (ClawHub-distributed)
+├── pi/                     ← pi extension source (ships raw .ts; pi compiles at load)
+└── bundle/                 ← unified `hivemind` CLI build output
 ```
 
 ## Security