@deeplake/hivemind 0.7.49 → 0.7.51

package/.claude-plugin/marketplace.json

@@ -6,18 +6,18 @@
   },
   "metadata": {
     "description": "Cloud-backed persistent shared memory for AI agents powered by Deeplake",
-    "version": "0.7.49"
+    "version": "0.7.51"
   },
   "plugins": [
     {
       "name": "hivemind",
       "description": "Persistent shared memory powered by Deeplake — captures all session activity and provides cross-session, cross-agent memory search",
-      "version": "0.7.49",
+      "version": "0.7.51",
       "source": {
         "source": "git-subdir",
         "url": "https://github.com/activeloopai/hivemind.git",
         "path": "claude-code",
-        "sha": "032c528d737ea200593cc7a16785e1954f9c66b2"
+        "sha": "c0c861150a00e85bc4fd21120ae2a331417468d0"
       },
       "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": "0.7.49",
+  "version": "0.7.51",
   "author": {
     "name": "Activeloop",
     "url": "https://deeplake.ai"

package/README.md

@@ -16,6 +16,7 @@
   <a href="LICENSE"><img src="https://img.shields.io/badge/License-Apache%202.0-blue.svg" alt="License"></a>
   <a href="package.json"><img src="https://img.shields.io/badge/node-%3E%3D22.0.0-brightgreen.svg" alt="Node"></a>
   <a href="https://deeplake.ai"><img src="https://img.shields.io/badge/Powered%20by-Deeplake-orange.svg" alt="Deeplake"></a>
+  <a href="https://www.ycombinator.com"><img src="https://img.shields.io/badge/Y%20Combinator-backed-ff6600.svg" alt="Y Combinator backed"></a>
 </p>
 
 <p align="center">
@@ -26,14 +27,35 @@
 >
 > Tuesday, every agent on the team can execute the pattern.
 
-**Beyond memory.** Hivemind captures every coding-agent interaction in your org as a structured trace, codifies repeated patterns into reusable skills, and propagates those skills to every agent on your team.
+On [LoCoMo](https://arxiv.org/abs/2402.17753), the public long-context memory benchmark, Hivemind is **25% cheaper, 1.7× fewer tokens, and 31% fewer turns** than running without shared memory. ([See the numbers below.](#benchmarks))
+
+**Beyond memory.** Hivemind doesn't just remember — it mines your team's traces for repeated patterns and codifies them into reusable skills that propagate back into every agent on the team. The agent your junior engineer used this morning is sharper because of what your senior engineer's agent figured out last week.
 
 - 📥 **Captures** every session's prompts, tool calls, and responses as structured traces in Deeplake
-- 🧠 **Codifies** patterns in those traces into reusable skills, available to every agent on your team
-- 🔍 **Searches** across all traces and skills with lexical retrieval (grep fallback when index unavailable)
+- 🧠 **Codifies** patterns into reusable `SKILL.md` files, available to every agent on your team
+- 🔍 **Searches** traces and skills with hybrid lexical + semantic retrieval (BM25 fallback when embeddings off)
 - 🔗 **Propagates** capability across sessions, agents, teammates, and machines in real time
 - 📁 **Intercepts** file operations on `~/.deeplake/memory/` through a virtual filesystem backed by SQL
 - 📝 **Summarizes** sessions into AI-generated wiki pages via a background worker at session end
+- ☁️ **BYOC**: keep data in your own GCS, Azure, S3, or on-prem bucket — [see Security & storage](#security--storage)
+
+## Benchmarks
+
+On the [LoCoMo](https://arxiv.org/abs/2402.17753) long-context memory benchmark (100 QA pairs, Claude Haiku via `claude -p`, hybrid lexical + semantic retrieval), Hivemind cuts cost, tokens, and turns versus a no-memory baseline:
+
+| Metric            | Baseline | Hivemind | Improvement      |
+|-------------------|----------|----------|------------------|
+| Cost / 100 QA     | $8.94    | $6.65    | **25% cheaper**  |
+| Tokens / question | 1,700    | 1,008    | **1.7× fewer**   |
+| Turns / question  | 8.9      | 6.2      | **31% fewer**    |
+
+The agent reaches the answer in fewer turns with less context, because the prior work is already in scope at recall time — not re-derived per session.
+
+<p align="center">
+  <a href="https://star-history.com/#activeloopai/hivemind&Date">
+    <img src="https://api.star-history.com/svg?repos=activeloopai/hivemind&type=Date" alt="Star History Chart" width="600">
+  </a>
+</p>
 
 ## Quick start
 
@@ -285,26 +307,16 @@ hivemind skillify unpull                     # remove pulled skills
 
 Triggers, generation flow, full `pull` / `unpull` semantics, gate-CLI table per agent, env vars, logs: **[docs/SKILLIFY.md](docs/SKILLIFY.md)**.
 
-## Rules + tasks (cross-agent KPIs)
+## Rules (cross-agent team principles)
 
-Hivemind **shares team rules and tasks across every agent in the org**, injected at SessionStart so every claude-code / cursor / hermes session starts knowing them. Tasks come with LLM-generated KPIs; the agent records progress via a CLI; `tasks report` shows current/target.
+Hivemind **shares team rules across every agent in the org**, injected at SessionStart so every claude-code / cursor / hermes session starts knowing them. For personal or team work items with progress tracking, use [Goals + KPIs](#goals--kpis) (VFS-backed) instead.
 
 ```bash
-# Rules — team-wide principles ("never DROP TABLE on prod")
 hivemind rules add "no DROP TABLE on prod creds"
 hivemind rules list                          # latest 10 active
 hivemind rules edit <rule-id> "<new text>"   # bumps version
 hivemind rules done <rule-id>                # mark closed
 
-# Tasks — personal or team work items, with agent-generated KPIs
-hivemind tasks add "ship the search bar" [--scope me|team] [--assign <user>]
-hivemind tasks list [--mine|--team|--all] [--status active|done|all]
-hivemind tasks edit <task-id> "<new text>"
-hivemind tasks done <task-id>
-hivemind tasks assign <task-id> <user>
-hivemind tasks progress <task-id> <kpi-id> --value N [--note "..."]
-hivemind tasks report [<task-id>]            # SUM events per KPI
-
 # Cross-agent diagnostic / pi/openclaw fallback
 hivemind context                             # print the injection block on demand
 ```
@@ -318,36 +330,28 @@ fall back to `hivemind context`):
 - <rule_id>: <text>
 (X more — run 'hivemind rules list' to see all)
 
-=== HIVEMIND TASKS (N active) ===
-[team] <task_id>: <text> ★YOU | PRs merged: 3/5 count
-[me]   <task_id>: <text>      | Lines reviewed: 75/200 lines
-(X more — run 'hivemind tasks list' to see all)
-
 === HIVEMIND HOW-TO ===
 - Rules above are team principles. Treat any action that would violate one as a critical error and surface it to the user before proceeding.
-- Tasks above are your current work. Use 'hivemind tasks progress <task-id> <kpi-id> --value N' to record progress on a KPI.
-- Run 'hivemind rules list' / 'hivemind tasks list' for the full inventories beyond what's shown here.
+- Run 'hivemind rules list' for the full inventory beyond what's shown here.
 ```
 
-**Auto-extract** — `gh pr merge` from inside an agent's Bash tool
-appends an event to `hivemind_task_events` automatically (failed
-merges, `--auto` enablement, interrupted commands all skipped). The
-event is "orphan" in v1 (no task binding yet); v1.1 ships
-`hivemind events attribute` for retroactive binding.
-
-**KPI generation** — `hivemind tasks add` calls Claude Sonnet to
-produce 1-3 KPIs from the task text. Failure modes (no API key,
-timeout, parse error) degrade to empty kpis; the task still INSERTs
-and the user can record progress manually.
-
 **Env vars:**
-- `HIVEMIND_RULES_TABLE`, `HIVEMIND_TASKS_TABLE`, `HIVEMIND_TASK_EVENTS_TABLE` — table names (default `hivemind_rules` / `hivemind_tasks` / `hivemind_task_events`).
-- `HIVEMIND_KPI_MODEL` — model id for KPI generation (default `claude-sonnet-4-6`).
-- `HIVEMIND_KPI_LLM=disable` — opt out of LLM KPI gen.
-- `ANTHROPIC_API_KEY` — required for KPI gen; absence is a silent no-op (kpis = `[]`).
+- `HIVEMIND_RULES_TABLE` — table name (default `hivemind_rules`).
 - `HIVEMIND_CAPTURE=false` — full read-only mode. Skips placeholder + ensure DDL; renderer still injects.
 
-Full data model, identity contract, per-agent injection status, auto-extract pipeline, KPI LLM details, and known v1 limitations: **[docs/RULES_TASKS_KPIS.md](docs/RULES_TASKS_KPIS.md)**.
+## Goals + KPIs
+
+Personal / team objectives + measurable targets live in the Deeplake virtual filesystem under `~/.deeplake/memory/goal/<owner>/<status>/<uuid>.md` and `~/.deeplake/memory/kpi/<goal_id>/<kpi-slug>.md`. Path encodes structure (owner, status, goal_id); the file body holds the human-readable description.
+
+```bash
+# CLI fallback for runtimes that can't route VFS writes (cursor/hermes/pi)
+hivemind goal add "ship the search bar"
+hivemind goal list [--all|--mine]
+hivemind goal done <goal_id>
+hivemind goal progress <goal_id> opened|in_progress|closed
+```
+
+For VFS-capable runtimes (claude-code/codex) the `hivemind-goals` skill creates and edits goals/KPIs directly via Bash heredoc against the VFS path — `mv` between `opened/`, `in_progress/`, and `closed/` is the canonical status transition. KPIs are manual files; the body format is documented in the skill (`target:`, `current:`, `unit:`).
 
 ## Architecture
 
@@ -360,13 +364,37 @@ Per-agent integration mechanisms (marketplace plugin, hooks, skills, native exte
 - **Skill versioning and review.** Pre-release human review for codified skills before they propagate org-wide, for teams that want a curation step.
 - **More agents.** If your team uses an agent that isn't on the supported-assistants list above, open an issue.
 
-## Security
+## Security & storage
+
+### Tenant isolation & encryption
+
+- TLS between every agent and Deep Lake. AES-256 on the bytes once they land. Your cloud credentials live in Deep Lake's vault — Hivemind never sees the raw keys.
+- Org and workspace boundaries enforced at the storage layer, not just the API. Sessions never share a row, a partition, or an index with another workspace.
+- Disable capture per session with `HIVEMIND_CAPTURE=false`. Delete a workspace and the underlying objects go with it.
+
+### Code-level controls
 
 - SQL values escaped with `sqlStr()`, `sqlLike()`, `sqlIdent()`
 - ~70 allowlisted builtins run in the virtual FS; unrecognized commands are denied
 - Credentials stored with mode `0600`, config dir with mode `0700`
 - Device flow login: no tokens in environment or code
-- `HIVEMIND_CAPTURE=false` fully disables data collection
+
+### Bring your own cloud (BYOC)
+
+Hivemind Cloud is the default. When that isn't enough, point Hivemind at storage in your own cloud — we handle the orchestration, data never leaves your perimeter.
+
+| Provider                   | Status     | Setup                                                  |
+|----------------------------|------------|--------------------------------------------------------|
+| Google Cloud Storage       | Available  | [docs](https://docs.deeplake.ai/latest/guide/gcs/)     |
+| Azure Blob Storage         | Available  | [docs](https://docs.deeplake.ai/latest/guide/azure/)   |
+| Amazon S3                  | Available  | [contact us](https://deeplake.ai/hivemind#security)    |
+| S3-compatible on-prem      | On request | [contact us](https://deeplake.ai/hivemind#security)    |
+
+## Who builds Hivemind
+
+Hivemind is built and maintained by [Activeloop](https://activeloop.ai) — the open-source team behind [Deeplake](https://github.com/activeloopai/deeplake), backed by Y Combinator.
+
+We run Hivemind ourselves, all day, across Claude Code, OpenClaw, Codex, and Cursor. Every benchmark number above came from our own internal eval against the LoCoMo public benchmark. If you're running coding agents at a team or org and want to talk through your setup, drop us a line: [hello@activeloop.ai](mailto:hello@activeloop.ai).
 
 ## Development