AIAny
AI Agent2026
Icon for item

Obsidian Mind

Provides AI coding agents with persistent memory inside an Obsidian vault—preserving session context, decisions, and notes across sessions. Integrates hooks/commands for Claude Code, Codex CLI, and Gemini CLI and optionally uses QMD for semantic recall; aimed at developer workflows.

Introduction

Most LLM-based coding sessions start from zero: context, decisions, and informal notes rarely carry over. Obsidian Mind takes a vault-first approach so an agent's "brain" is git-tracked markdown—not an ephemeral prompt. That makes session state durable, linkable, and searchable without forcing a hosted memory store.

What Sets It Apart
  • Vault-first persistent memory: instead of dumping context into a short-lived prompt, the project writes structured notes (people, decisions, incidents, 1:1s) into an Obsidian vault so every session can build on prior work. This makes evidence traceable via backlinks and git history.

  • Agent-agnostic hooks and commands: the same lifecycle hooks, slash commands, and subagents work with Claude Code (full support), Codex CLI, and Gemini CLI. So teams can standardize a memory/operational layer independent of the LLM provider.

  • Semantic retrieval opt-in (QMD) + token efficiency: QMD provides semantic recall and ranked retrieval so the agent only loads narrowly relevant content. When QMD is absent the system falls back to grep/Obsidian CLI, keeping the template usable on lightweight setups.

  • Built-in workflows for developer use: commands like /om-standup, /om-dump, /om-incident-capture and subagents (brag-spotter, slack-archaeologist, review-prep) map common engineering rituals to durable notes and indexes, reducing repeated explanations across sessions.

Who It's For & Trade-offs

Great fit if you are an engineer or small team who already uses Obsidian (or values a plaintext, git-tracked memory) and want agents to accumulate context, decisions, and performance evidence across sessions. It favors local control, auditability, and integration with CLI-driven agent workflows.

Look elsewhere if you need a turnkey hosted memory service, minimal local setup, or non-technical end-user UX: the template expects Obsidian 1.12+, Node 22+, optional QMD model downloads (hundreds of MB–GB), and some CLI familiarity. Also, because notes are local files, you must manage sync/backup and any org security concerns yourself.

More Items

Turns fragile, implicit search progress into explicit, persistent, shared state for multi-agent information seeking — externalizes progress as Frontier Task, Evidence Graph, Coverage Map and Failure Memory, and uses pipeline-parallel scheduling plus a middleware harness to avoid repeated failed searches and improve utilization and throughput.

GitHub
AI Agent2026

Provides a lightweight Python harness that turns LLMs into working agents with tool-use, skills, persistent memory, permission controls and multi-agent coordination. Ships with a CLI/React TUI, 43+ built-in tools, a plugin/skill system and the ohmo personal-agent for chat gateways. Best for developers prototyping agent workflows and multi-agent experiments.

GitHub
AI Client2025

Turns Chromium into a local-first AI browser with an embedded assistant that can summarise pages, extract structured data, automate web tasks, and run scheduled agents. Built as an open-source Chromium fork with 53+ built-in browser tools, 40+ app integrations, and support for BYO AI keys or fully local models (Ollama / LM Studio).