hive-vault
Your AI coding assistant forgets everything between sessions. Hive fixes that.
Hive is an MCP server that connects your AI assistant to an Obsidian vault. Instead of loading everything upfront, it queries only what's needed — on demand.
| Metric | Without Hive | With Hive |
|---|---|---|
| Context loaded per session | ~800 lines (static) | ~50 lines (on demand) |
| Token cost for context | 100% every session | 6% average per query |
| Knowledge retained between sessions | 0% | 100% (in vault) |
Measured on a real vault with 19 projects, 200+ files. See benchmarks.
Quick Start
Hive runs without a vault — vault tools return a friendly error until VAULT_PATH is set, so you can install first and configure later.
# Minimal — uses default vault path ~/Projects/knowledge
claude mcp add -s user hive -- uvx --upgrade hive-vault
# With a custom vault path
claude mcp add -s user hive -e VAULT_PATH=$HOME/path/to/vault -- uvx --upgrade hive-vault
# Gemini CLI
gemini mcp add -s user -e VAULT_PATH=$HOME/path/to/vault hive-vault uvx -- --upgrade hive-vault
Default vault path:
~/Projects/knowledge. Override withVAULT_PATH(orHIVE_VAULT_PATH) as shown above.
For Codex CLI, GitHub Copilot, Cursor, Windsurf, and other clients, see Getting Started.
Then ask your assistant: "Use vault_list to see my vault"
Requirements
Hive degrades gracefully — every recommended or optional dependency reveals more capability without breaking the baseline.
-
Required
- Python 3.12+ (works on 3.13).
- A directory of markdown files. The vault structure used by
00_meta/10_projects/50_work/80_agentsis optional — without it, vault tools still operate but the scope routing is flat.
-
Recommended
gitinitialised inside the vault. Without it,vault_write/vault_patchstill write to disk; they just skip the per-write commit (andvault_commitreports the working tree as untracked).- The Obsidian desktop app to author the vault by hand.
- The obsidian-git plugin with auto-commit set to 5–10 minutes. Pair it with
vault_write(commit=False)/vault_patch(commit=False)to push the git workload off the synchronous tool path; see Recommended configuration below.
-
Optional
- Ollama running
qwen2.5-coder:7b(or compatible) for local, freedelegate_task/capture_lessonworker calls. - An OpenRouter API key (
OPENROUTER_API_KEY) as a free-tier and paid fallback worker. - A backup git remote (e.g. private GitHub repo) so vault history survives a disk loss.
- Ollama running
Recommended configuration
Per ADR-006 (commit policy), the recommended pairing for write-heavy flows is:
- Install and enable the obsidian-git plugin in your vault.
- Set its auto-commit interval to 5 or 10 minutes.
- Call
vault_write(..., commit=False)andvault_patch(..., commit=False)for all bulk operations. - Optionally call
vault_commit(message="...")at the end of a session to force a checkpoint sooner than the obsidian-git tick.
vault_health reports a ## external_committer block when it detects obsidian-git in the vault. The commit=False durability contract is explicit: files are persisted to disk regardless; only the commit is deferred. A crash before the next flush loses the commit, not the content.
When a tool call is cancelled mid-flight (slow worker, client timeout), the server may have already mutated the disk before the cancel ack reaches the wire. vault_health surfaces a ## ghost_responses counter and emits a mcp.ghost_response.suppressed_after_cancel_ack WARNING for each event — verify state via vault_query rather than retrying, since the ErrorData ack does not imply rollback (ADR-007).
Daemon mode (optional)
The default uvx hive-vault runs a fresh server per session. Daemon mode instead runs one long-lived hive serve that owns the vault, with each session connecting through a thin hive client shim — useful for concurrent sessions, single-owner guarantees (ADR-011), and automatic version adoption. It always degrades to an in-process server if the daemon is down, so it never breaks a session.
uv tool install --upgrade hive-vault # >= 1.32.0
hive service install # supervise hive serve (systemd --user / Task Scheduler)
To install a newer release, use the platform-specific command:
# Linux / macOS
uv tool upgrade hive-vault
# Windows (the version is optional; omitted selects the latest PyPI release)
hive self-upgrade [version]
On Windows, self-upgrade builds the release beside the running files and atomically switches
the managed runtime, avoiding in-use-file conflicts. Open a new terminal after the first managed
upgrade so its PATH change is available. Once supervised, the daemon detects the new installed
version, exits 75, and the supervisor restarts it into the new code. See the
daemon mode guide and the
activation runbook.
Tools
| Tool | What it does |
|---|---|
vault_query |
Load project context, tasks, roadmap, lessons — or any file by path |
vault_search |
Full-text search with metadata filters, regex, ranked results, recent changes, lesson-usage ranking (rank_by) |
vault_list |
Browse projects and files with glob filtering |
vault_health |
Server identity (version, vault path, backends), health metrics, drift detection, usage stats, opt-in runtime block |
vault_write |
Create, append, or replace vault files. commit=False defers the git commit for batching |
vault_patch |
Surgical find-and-replace. commit=False defers the git commit for batching |
vault_commit |
Flush pending commit=False writes into one git commit |
capture_lesson |
Capture lessons inline / batch-extract from text / look up existing lessons by keyword (find=) |
session_briefing |
Tasks + lessons + git log + health in one call |
delegate_task |
Route tasks to cheaper models or summarize vault files |
worker_status |
Budget, connectivity, available models |
Plus 5 resources and 4 prompts for guided workflows.
Lesson reinforcement
Every read of a lesson via vault_query, vault_search, or capture_lesson(find=…) increments a counter and grows that lesson's confidence asymptotically toward 1.0. Validated lessons rank higher than one-shot captures over time.
# Surface the top-ranked lessons matching a keyword
capture_lesson(project="hive", find="multi-process")
# Search lessons ranked by usage signal (not BM25)
vault_search(query="timeout", rank_by="reinforcements") # most-reinforced first
vault_search(query="timeout", rank_by="confidence") # highest decayed confidence
vault_search(query="timeout", rank_by="hybrid") # α=0.7 BM25 + 0.3 confidence
Storage: SQLite side-table at HIVE_LESSON_DB_PATH (default ~/.local/share/hive/lesson_reinforcement.db). WAL mode + busy_timeout make it cross-process safe.
Architecture
MCP Host (Claude Code, Gemini CLI, Codex CLI, Cursor, ...)
└── hive-vault (MCP server, stdio)
├── Vault Tools (7) ── Obsidian vault (Markdown + YAML frontmatter)
├── Session Tools (1) ── Adaptive context assembly
└── Worker Tools (2) ── Ollama (free) → OpenRouter free → paid ($1/mo cap) → reject
Documentation
Full documentation at mlorentedev.github.io/hive:
- Getting Started — install for all MCP clients
- Configuration — all 19 environment variables
- Vault Structure — how to organize your vault
- Use Cases — real-world workflows
- Architecture — module map and design decisions
- Troubleshooting — common issues and fixes
Project-bound knowledge (docs-as-code) lives in docs/:
docs/adr/— Architecture Decision Recordsdocs/runbooks/— operational proceduresdocs/troubleshooting/— known issues and root-cause write-upsdocs/lessons.md— accumulated gotchas and post-mortems
Contributing
See CONTRIBUTING.md for setup and PR workflow.
git clone https://github.com/mlorentedev/hive.git && cd hive
make install # create venv + install deps
make check # lint + typecheck + test (478 tests, 90% coverage)
License
1 maintainer
Release files for hive-vault 4.2.2
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | |
|---|---|---|---|
| hive_vault-4.2.2.tar.gz | 915.8 kB | Details |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Reset |
|---|---|---|---|---|
| hive_vault-4.2.2-py3-none-any.whl | Python 3 | none | any | Details |
Total release size: 1.1 MB
Release files / hive_vault-4.2.2.tar.gz
| Download URL | hive_vault-4.2.2.tar.gz |
|---|---|
| Size | 915.8 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
a3ff125a27f96dda5532d0eb5d9121138401f02be2f43d93474363b3459647bc
|
|
BLAKE2b-256 checksum How to use checksums |
627433279df3e0d12281da7a117dc0ed266468722f38fce43eb15bf1f82c833b
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/7.0.0 CPython/3.13.14
|
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Sep 26, 2026.
Transparency logRelease files / hive_vault-4.2.2-py3-none-any.whl
| Download URL | hive_vault-4.2.2-py3-none-any.whl |
|---|---|
| Size | 172.0 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
5cc5c6d2b819e939ac38e8799740477c7b9c983faf91fa87f6bce64959ebe609
|
|
BLAKE2b-256 checksum How to use checksums |
477240abce935754c941416dae5a1dbb9c1113e2c37cf784dd1f044fc155e26e
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/7.0.0 CPython/3.13.14
|
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Sep 26, 2026.
Transparency log
