# neurostack

> Your second brain, starting today. CLI + MCP server that helps you build, maintain, and search a knowledge vault that gets better every day. Works with any AI provider. Local-first, zero-prereq instal

- **URL**: https://www.freshcrate.ai/projects/neurostack
- **Author**: raphasouthall
- **Category**: MCP Servers
- **Latest version**: `v0.13.0` (2026-05-05)
- **License**: Apache-2.0
- **Source**: https://github.com/raphasouthall/neurostack
- **Homepage**: https://neurostack.sh
- **Language**: Python
- **GitHub**: 41 stars, 3 forks
- **Registry**: github
- **Tags**: `ai-memory`, `knowledge-graph`, `local-ai`, `local-first`, `markdown`, `mcp`, `mcp-server`, `neuroscience`, `python`

## Description

Your second brain, starting today. CLI + MCP server that helps you build, maintain, and search a knowledge vault that gets better every day. Works with any AI provider. Local-first, zero-prereq install.

## Recent releases

| Version | Date | Urgency | Changes |
| --- | --- | --- | --- |
| `v0.13.0` | 2026-05-05 | High | ## Breaking change  **Removed `vault_capture` MCP tool and `neurostack capture` CLI command.**  The tool wrote directly to `{vault_root}/inbox/` without git tracking, indexing, or any path back to origin. In runtimes where the vault is a read-replica (e.g. an indexer container pulling from git), captured files were stranded on the replica's filesystem and invisible to every other tool — including NeuroStack's own search and ask. The architectural promise that *your Markdown files are never modif |
| `v0.11.1` | 2026-03-27 | Medium | ## Critical fixes from 10-agent stochastic audit  ### Security - **OAuth PKCE verification** — `/oauth/token` never verified `code_verifier` against the stored `code_challenge`, making PKCE completely broken. Auth codes are now opaque, PKCE-bound, one-time-use tokens with 10-minute TTL. Redirect URI validation added against registered clients.  ### Billing - **MCP rate limiting tier resolution** — All MCP tool calls hardcoded `tier: "free"`, causing pro/team users to be incorrectly throttled. Ti |
| `v0.11.0` | 2026-03-26 | Medium | **Full Changelog**: https://github.com/raphasouthall/neurostack/compare/v0.10.4...v0.11.0 |
| `v0.10.4` | 2026-03-26 | Medium | ## Phase 1: Cloud Sync Foundation  Client-side infrastructure for the sync pipeline.  ### Bug Fixes - **Fixed ghost entries** — `push()` now transmits `diff.removed` file list to the server, so deleted vault files are purged from the cloud index  ### New Features - **CloudClient 21-tool parity** — all MCP tools now work in cloud mode via REST dispatch - **Cloud dispatch layer** — automatic mode-based routing (local SQLite vs cloud API) - **Init default flipped to cloud mode** — new users default |
| `v0.10.3` | 2026-03-26 | Medium | ## New Features  - **Windows support** — NeuroStack can now be installed and run on Windows via `npm install -g neurostack`  ### Installation layer (npm) - Added `win32` to supported platforms - uv auto-install uses `.zip` download + PowerShell `Expand-Archive` on Windows - Fallback installer uses PowerShell (`irm \| iex`) instead of `sh` - `command -v` replaced with `where` for command lookup - CLI wrappers created as `.cmd` batch files instead of bash scripts - Platform-aware PATH separator, co |
| `v0.10.2` | 2026-03-26 | Medium | ## Bug Fixes  - **fix(mcp): wrap vault_search full-depth return in dict** — The `depth="full"` code path returned a list instead of a dict, causing Pydantic output validation to fail. This was the last remaining case missed by the list-to-dict fix in v0.10.1 (commit 0d6a751). All other depth modes (`auto`, `triples`, `summaries`) were unaffected.  ## Full MCP Tool Audit  All 21 MCP tools tested end-to-end. 20/21 passed — the only failure was the bug fixed above. |
| `v0.10.1` | 2026-03-25 | Medium | ## What's New  ### One-command setup  `neurostack init` now handles the entire onboarding flow:  ``` npm install -g neurostack neurostack init ```  The interactive wizard walks through: 1. **Cloud or Local?** — cloud uses Gemini, local uses Ollama 2. **Lite or Full?** — lite = FTS5 only, full = embeddings + summaries + communities 3. **Ollama models** — choose embedding and LLM models, auto-pull 4. **Vault path + profession pack** — point to existing notes or start fresh 5. **LLM endpoint config |
| `v0.10.0` | 2026-03-25 | Medium | ## What's New  ### Neuroscience-grounded reranking (replaces cross-encoder)  Three new scoring signals in `hybrid_search`, using only existing embeddings in SQLite — zero external models, zero network calls:  - **Energy landscape convergence confidence** — measures how representative the matched chunk is of its note's overall embedding distribution. Based on Hopfield attractor basin dynamics: deep narrow wells (low chunk variance) score higher than broad shallow ones. - **Lateral inhibition** — |
| `v0.9.5` | 2026-03-25 | Medium | **Full Changelog**: https://github.com/raphasouthall/neurostack/compare/v0.9.4...v0.9.5 |
| `v0.9.4` | 2026-03-25 | Medium | **Full Changelog**: https://github.com/raphasouthall/neurostack/compare/v0.9.2...v0.9.4 |

## Citation

- HTML: https://www.freshcrate.ai/projects/neurostack
- Markdown: https://www.freshcrate.ai/projects/neurostack.md
- Dependencies JSON: https://www.freshcrate.ai/api/projects/neurostack/deps

_Generated by freshcrate.ai. Indexes github releases for AI-agent ecosystem packages._