AgentIndex icon
AgentIndex
ToolsMCP ServersHOTCategoriesTrendingNewBest ListsCompareGuides
Submit Tool
ToolsMCP ServersHOTCategoriesTrendingNewBest ListsCompareGuides
Home/
Memory & Context/
obsidian-second-brain
obsidian-second-brain logo

obsidian-second-brain

Active·★ 5.4k·MIT·Updated 2026-11-16

Obsidian Second Brain stores agent knowledge and context in Markdown, while its Crew feature provides a shared job log for multiple agent hosts. Crew also works in a plain folder without Obsidian. This is useful when a team wants inspectable handoff records and accepted lessons before adopting a more elaborate memory service. We reviewed the Crew workflow at a fixed 0.20.0 source revision using Python 3.12.13. The local runtime uses the standard library; the broader research and vault features have separate requirements.

Ten checks exercised the actual command entry point with three filesystem resolvers redirected to temporary destinations. Setup reruns preserved unrelated rules and did not duplicate hooks. A job was consumed once by one session and remained independently readable by another session. An open lesson did not change recipient rules; explicit keep promoted it once, and an opposite final decision was rejected. Independent CLI processes retained all 24 concurrent local writes. Malformed hook JSON stopped setup without rewriting existing rules. No real agent configuration or existing vault was modified.

An important limit appeared with bounded unread reads: only the latest requested records were displayed, but older omitted history was also marked consumed. Use a digest or inspect the log for complete historical review. The human keep convention is not authenticated enforcement, and local concurrent writes do not establish distributed synchronization safety. We did not load generated hooks in a host, call a model, assess semantic retrieval or test automatic vault rewriting. Choose Crew for a narrow file-based handoff trial, then separately verify that the chosen host receives and uses its context.

Read the full review, verification scope and sources →

Hands-on tested · Tested on 2026-11-05 with 0.20.0; commit deff215377f0ecae68deed1074046f883425388e (Crew local workflow only).

Setup: macOS arm64; Node.js 26.6.0, CPython 3.12.13; selected modules and temporary synthetic files only

Commands run

python3.12 doc/review-fixtures/memory-video-20261105/verify.py --sources <source-parent> --output /tmp/memory-video-results.json

What we saw

  • Ten local Crew checks passed with three path resolvers redirected; no real host settings changed.
  • 24 concurrent jobs retained; per-session readers and explicit keep behaved as recorded.
  • Bounded unread reads consumed omitted history. No model, hook activation, semantic retrieval, vault rewrite or distributed-sync test.

Data as of 2026-11-12.

License
MIT
Latest release
v0.20.0 · 2026-10-25
Last commit
2026-11-10
Contributors
55
Forks
646
Open issues and PRs
7
First published
2026-03-24

Source: GitHub, npm and PyPI public APIs.

#agent-memory#agent-skills#ai-agents#ai-note-taking#ai-second-brain#claude#claude-code#claude-code-skill
$ Install
$ /plugin marketplace add eugeniughelbur/obsidian-second-brain && /plugin install obsidian-second-brain@obsidian-second-brain
↗ Visit site★ GitHub
01

Features

01Persistent knowledge in portable Markdown files
02Capture, search and maintenance commands
03Multiple host builds from one source tree
04Crew shared job log with human-reviewed lessons
02

Why choose it

+All 24 concurrent local CLI job writes were retained in the shared log.
+Open lessons did not affect rules; explicit keep promoted once and repeated keep was stable.
+Setup reruns preserved unrelated rules; malformed hook JSON stopped rewriting.
03

Trade-offs

!Limited unread reads mark older omitted records as consumed, requiring digest for full history.
!Human keep is a caller convention, not authenticated approval enforcement.
!Host activation, semantic retrieval, vault rewriting and distributed sync were not tested.
05

Maintenance check

ActiveChecked: 2026-11-12
Last commit
2026-11-10
Commits, last 90 days
100+
Releases, last 90 days
7
Latest release
v0.20.0 (2026-10-25)
Open issues
7
Recent issues with at least one comment
11/15
Commits per week, last 12 weeks
Commits per week, last 12 weeks: 11, 26, 5, 36, 12, 11, 5, 7, 25, 14, 10, 11

Oldest week on the left; the latest four weeks are orange. Source: GitHub commit activity.

Status rule: archived on GitHub = Archived; last commit within 90 days = Active; 91 to 365 days = Slowing; older = Stale. All figures come from the GitHub API on the date shown.

Most discussed open issues

  • #171 Own a platform build: six of eight are open29 comments · 2026-07-26
  • #337 [Feature] Add opt-in Parallel Search MCP to free research4 comments · 2026-10-11
  • #163 i18n: add trigger phrases for a new language4 comments · 2026-07-26
  • #398 [Feature] Crew: let decided lessons leave hook reads, and keep hook reads under the host's size limit2 comments · 2026-11-09
  • #386 Search falls back to lexical without a word when the embedder is slow2 comments · 2026-11-04

Issue titles are quoted from GitHub. Open the link to check whether a problem still applies to the version you use.

04

Who it fits

Pick it if
  • You want readable job handoffs in a plain local folder.
  • You will review lessons and separately verify host-visible context.
Look elsewhere if
  • You need measured semantic-memory accuracy or automatic task coordination.
  • You require distributed consistency or authenticated lesson approval.
06

Compatibility

Obsidian
Vault workflow; Crew can use a plain folder
Verified via docs
Agent Skills
Portable host build documented
Verified via docs
Python
Crew requires 3.10+
Verified via docs
07

Quick start

1
$ /plugin marketplace add eugeniughelbur/obsidian-second-brain
2
$ /plugin install obsidian-second-brain@obsidian-second-brain
08

Use cases

↳Retaining project context across agent sessions
↳Organizing research and decisions in an Obsidian vault
↳Sharing job records among coding agents
09

Alternatives

⚡Top VS:
VSorigin★498→VScognee★33.4k→VSplanning-with-files★28.1k→VScontext-mode★34.2k→
origin logo
origin★ 498
Local-first Rust daemon for AI work. Git-versioned memories, distilled wiki pages, sessions for Claude Code, Cursor, Codex, and any MCP client.
VSCompare→
cognee logo
cognee★ 33.4k
Cognee is the open-source AI memory platform for agents. Give your AI agents persistent long-term memory with small models for free
VSCompare→
planning-with-files logo
planning-with-files★ 28.1k
Persistent file-based planning for AI coding agents and long-running tasks. Crash-proof markdown plans, session recovery after /clear and compaction, per-turn re-injection against context rot, deterministic completion gate. Manus-style. Install from npm, the Claude Code plugin marketplace, or npx skills. Codex, Cursor, OpenCode, 60+ agents.
VSCompare→
context-mode logo
context-mode★ 34.2k
Context window optimization for AI coding agents. Sandboxes tool output, 98% reduction. 12 platforms
VSCompare→
obsidian-wiki logo
obsidian-wiki★ 3.8k
Framework for AI agents to build and maintain a digital brain through Obsidian wiki | Memory System for Agents
VSCompare→
Claude Code Templates logo
Claude Code Templates★ 33.9k
Open-source registry and CLI for Claude Code components: agents, commands, skills, hooks, MCPs, settings and mods
VSCompare→
PrismerCloud logo
PrismerCloud★ 1.4k
Prismer Cloud
VSCompare→
AgentRecall-MCP logo
AgentRecall-MCP★ 376
Persistent, correction-driven memory for AI agents. Cross-session, cross-platform (Claude Code, Codex, Gemini — any MCP client). Learns from mistakes, compresses context to save tokens, consolidates knowledge overnight. npm: agent-recall-mcp
See all alternatives →

Comments

Log in to leave a comment

No comments yet. Be the first!

On this page
01Features02Why choose it03Trade-offs05Maintenance check04Who it fits06Compatibility07Quick start08Use cases09Alternatives
eugeniughelbur /
obsidian-second-brain
↗

Shared Markdown job logs with explicit lesson retention

5.4k646MIT
Last commit2d ago
StatusActive
CategoryMemory & Context
Contributors55
Latest releasev0.20.0
Links
Documentation↗Discussion↗Issues↗Releases↗
Cloud Infrastructure
Ad

Deploy on DigitalOcean

Host your MCP servers, Docker containers, and AI agents with $200 free credit over 60 days.

Claim $200 Free Credit
© 2026 AgentIndex.app|Built by a 10-year iOS Developer.
Best by use caseAboutContactAdvertisePrivacy PolicyTerms of UseQYSGitHubBuy me a coffee ☕

Browse by Category

MCP ServersCode AssistantWorkflow AutomationRAG / Knowledge BaseMulti-AgentBrowser AutomationLLM InfraDev ToolingObservability

Not affiliated with Anthropic, OpenAI or Microsoft.