zhitongblog/solomd
Productivity · tested 2026-09-24 · by the Hlido desk, not the vendor
In short: A local-first Markdown editor with a bundled MCP server, so Claude Code / Cursor / Codex can drive your notes vault directly — a clean take on "agent-native" note-taking, with BYOK across 14 providers.
10 PASS · 0 FAIL of 10 public-surface claims
Quick answer
zhitongblog/solomd scores 82/100 (STEADY) on Hlido’s independent, hands-on test (reviewed 2026-09-24). STEADY reflects a well-maintained, MIT-licensed, local-first project with real release cadence, community download traction, and a coherent agent-native design (bundled MCP, BYOK). Pricing: Open source (free entry point documented).
SoloMD's pitch — "the editor where agents live" — is more precise than the usual AI-note-app copy. It is a small (~15 MB), MIT-licensed, Tauri-based Markdown editor that keeps your files as plain .md on disk, and its differentiator is a bundled MCP server: the same vault is editable by you in the app and drivable from outside by Claude Code, Cursor, or Codex over Model Context Protocol. That local-first, plain-files posture matters for lock-in — your data isn't trapped in a proprietary store — and the BYOK model across 14 providers means you aren't captive to one LLM vendor. The repository shows genuine maintenance (tagged releases, download counters, extensive multi-language READMEs, a public security page). The honest caveats: this is a single-author desktop app in a category crowded by Obsidian (with its own thriving plugin and MCP ecosystem), and the "scheduled recipes" / agent-surface features are the newest and least battle-tested part of the story. For someone who wants their notes to be first-class agent-addressable without leaving a local editor, it's a thoughtful, low-lock-in choice.
Why STEADY
STEADY reflects a well-maintained, MIT-licensed, local-first project with real release cadence, community download traction, and a coherent agent-native design (bundled MCP, BYOK). Not higher because it is a public-surface + repo-health assessment (medium confidence), it competes against the deeply entrenched Obsidian, and its agent-recipe features are recent and unproven at Hlido's evidence tier.
Public-surface checklist
- PASS Repo reachable (required) — GH API 200 for zhitongblog/solomd
- PASS Readme present (required) — README length 16368
- PASS License present (required) — MIT
- PASS Install documented (required) — install/usage section found in README
- PASS Active 12mo (required) — last push 4d ago
- PASS Releases present — latest v4.9.0
- PASS Community traction — 442 stars
- PASS Ci or tests — 3 workflow file(s)
- PASS Recent commit 90d — last push 4d ago
- PASS Agent consumable — MCP server markers in README
What we saw
1 screenshot captured by the Hlido engine during the reviewed run (run-ff84bc3760e21616-github-com). Our own captures — not vendor marketing material.
What it does well
- Local-first, plain .md files — low lock-in and portable data
- Bundled MCP server lets external agents (Claude Code / Cursor / Codex) drive the same vault
- BYOK across 14 providers — no single-LLM captivity
- Small footprint (~15 MB, Tauri) and MIT-licensed
- Strong maintenance signals: tagged releases, download counters, published security page, extensive localisation
What it fails at
- Competes head-on with Obsidian, which already has a mature plugin + MCP ecosystem
- Appears to be a single-maintainer project — bus-factor and long-term support risk
- The scheduled-recipes / agent-surface features are the newest and least proven part
- No public live demo Hlido could exercise; assessment is of the repo and stated behaviour
- Desktop-app distribution means no browsable web trial before download
Red flags
- Single-maintainer open-source project: verify release cadence and issue responsiveness before depending on it for critical workflows.
Best for
- Note-takers who want their vault to be directly addressable by coding agents via MCP
- Users who value local-first, plain-Markdown storage and low lock-in
- People who want to switch LLM providers freely (BYOK)
- Lightweight-editor fans who find full IDE-style tools overkill
Not recommended for
- Teams already deeply invested in Obsidian's plugin ecosystem with little reason to move
- Buyers who need enterprise support guarantees behind a single-maintainer project
- Users wanting a hosted, cross-device-sync-first notes service (this is local-first)
- Anyone needing a web trial before installing a desktop binary
Pricing & access
- ModelOpen source
- Free entry pointYes — a free tier or open-source edition is documented
Derived from Hlido-held evidence only (engine checklist + editorial text); quotes are verbatim from the scorecard; not vendor-supplied; re-derived daily. Verify current prices on the vendor's pricing page. Last verified 2026-07-16.
Related agents
Agent relevance
MCP
Agentic-Commerce Readiness 44/100 · SURFACE-ONLY
Independent readiness for agent delegation & transaction. How it’s scored · check live
Ships a bundled MCP server so MCP-capable clients (Claude Code, Cursor, Codex) can read and write the vault directly. Agent integration is the product's core design, not an afterthought.
Agent-friendly score: 7/10
Score over time
The longitudinal record — every point is the score as published on that date. Raw series.
Evidence
- Public repository reachable with substantive README — source (2026-09-24) verified
- Product description: "A markdown editor — and the bridge to your LLM. Local-first, MIT, ~15 MB. Bundled MCP server lets Claude Code / Codex / " — source (2026-09-24) verified
- Open-source license present in repository — source (2026-09-24) verified
scorecard.json · transparency passport · registry · methodology
Embed this trust badge
Markdown
[](https://hlido.eu/check/?agent=zhitongblog-solomd)HTML
<a href="https://hlido.eu/check/?agent=zhitongblog-solomd"><img src="https://hlido.eu/badge/zhitongblog-solomd.svg" alt="Hlido trust score"></a>