513 tagged local-first, measured the same way as everything else here.
Browse within: agent-memory 40macos 38knowledge-base 37knowledge-graph 34knowledge-management 25coding-agents 22electron 21model-context-protocol 21bun 18embeddings 18markdown 18Multi-Agent 16desktop-app 16ai-memory 15
brodewa369/roowet-semantic-vault-search
Instructions file CodexOpenCode
Instructions for brodewa369/roowet-semantic-vault-search, covering agents.md — hermes agent integration, mcp server config, init flow integration, session init — required and query classification (stage 5).
Instructions file
Claude Code instructions for opensauria/sauria, covering sauria — project rules, what is sauria, architecture, tech stack and project structure.
dimosgit/grounded-knowledge-engine
Instructions file CodexOpenCode
AGENTS.md instructions for dimosgit/grounded-knowledge-engine, covering agent guide, agent operating contract, authorship and attribution, two npm trees and commands — engine (repo root).
Instructions file
Instructions for Git-Rocky-Stack/Team-X, covering claude.md, inheritance from parent repositories, design system, key contacts and skill routing.
Instructions file
Claude Code instructions for QJ-Chen/agentlen, covering claude.md, product definition, canonical runtime flow, common commands and install.
Instructions file CodexOpenCode
Instructions for seemethere/spool, covering spool agent instructions, always read first, product direction, implementation stack and dogfooding readiness path.
AlekseiUL/hermes-codex-operator
Instructions file CodexOpenCode
Instructions for AlekseiUL/hermes-codex-operator, a project described as: A local-first operator that turns plain-language ideas into tracked, verified Codex work—planned by Hermes, executed by Codex, and explained back to you.
zaxardery8011-design/aiwff-runtime
Instructions file CodexOpenCode
Instructions for zaxardery8011-design/aiwff-runtime: This repository is a mock-first local runtime. Keep all work inside this repository unless the user explicitly asks for a separate path.
Instructions file CodexOpenCode
Instructions for OpenCoven/claude-code-cast, covering agents.md — claude-code-cast, branch & pr workflow, before opening the pr, repo-specific invariants (don't break these) and attribution — credit contributors correctly.
Instructions file
Instructions for AndreLYL/memkin, covering memkin — agent guide, session start, tool priority, saving signals and memory tiers.
Instructions file
Claude Code instructions for nimbus-agent/Nimbus, covering nimbus — claude code context, project overview, non-negotiables, security invariants and subsystems.
Instructions file CodexOpenCode
AGENTS.md instructions for unsoldgroup/mail-index, covering agent setup & usage guide, 1. register the mcp server, claude desktop, claude code and or with an absolute path / env.
Instructions file
Instructions for hbkdad/arc, covering claude.md, start every session with, non-negotiables (see master file for full list) and repo layout.
Instructions file CodexOpenCode
AGENTS.md instructions for AncientiCe/palace-rs, covering agent rules, 1. test-driven development (tdd), 2. quality gates on every task, 3. no plan markdown files and 4. internal api discipline.
Instructions file CodexOpenCode
Instructions for ctxfile/ctxfile, covering claude.md, project, hard rules, commands (run from repo root) and release checklist (every ship, no step skipped).
Instructions file CodexOpenCode
AGENTS.md instructions for hraness/wrench, a project described as: Open-source CLI and TypeScript SDK for precise web capabilities for AI agents: page capture, verified media archives, encrypted reads, and typed provider operations.
Instructions file CodexOpenCode
AGENTS.md instructions for hraness/atet, a project described as: Local-first AI media generation and video editing toolkit for coding agents, with a Bun CLI, TypeScript SDK, MCP server, and Agent Skill.
Instructions file
Instructions for zzallirog/weighted-compact, covering claude.md — weighted-compact root, substrate framing, tl;dr in 30 seconds, repo map and architectural invariants (locked).
Instructions file CodexOpenCode
AGENTS.md instructions for rezamotaghi/cbctscope, covering agents.md, what this is, hard rules, layout and the user manual.
Instructions file CodexOpenCode
AGENTS.md instructions for symphos-ai/orcho-mcp, covering orcho-mcp instructions, scope, local instruction files, workspace development pipeline and stable install is read-only.
Instructions file
Claude Code instructions for vvooki-sys/loomem, covering claude.md — rules for ai code generators in the loomem repo, router — read the subset that applies, five hard rules (never break these), build & run and repo map (where things live).
Instructions file
Instructions for pilotwaffle/TORQCLAW, covering claude.md — torqclaw, 1. repo context, instruction precedence, non-torq boundary and 2. governing harness.
Instructions file CodexOpenCode
Instructions for FramY2/ctxwise, a project described as: CtxWise — see and control what Codex loads. Local-first context audit, profiles, drift detection, and honest token receipts.
Instructions file CodexOpenCode
AGENTS.md instructions for frisco-deng/moradins-forge, covering agents.md, repo-local precedence, read first, agent adoption rules and deterministic commands.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: