local-first — independent software & tools
-
Relic
Local-first knowledge management powered by Markdown.
-
epicurus
Self-hosted, modular, local-first personal-assistant platform — an AI agent plus pluggable integration modules.
-
akashic-aurora
Memory for AI agents that learns what actually helped: lessons injected at the moment of action, credited by outcome, challenged by counter-evidence. Local-first, multi-agent, test-gated.
-
VecMem
Manage LLM agent memory with a resource-aware dual-tier system that uses HNSW indexing to balance short-term context and long-term knowledge retention.
-
Dezin
A local-first, tasteful design generator. Describe what you want; your own coding-agent CLI (Claude Code, Codex, Gemini, Cursor) builds it as a real artifact, held to a strict anti-AI-slop standard. BYOK, nothing leaves your machine.
-
busabase
⚡ The approval-first, open-source database & knowledge base for AI agents — review & approve every change before it's trusted. Local-first, self-hostable Airtable/Notion alternative.
-
clips-studio
Local-first AI clipping studio - turn long videos into ready-to-post vertical Shorts entirely on your own PC. Multimodal clip detection, speaker-aware face tracking, editable captions, AI edit chat. No cloud AI, no fees.
-
sportsdata-agents
Free, open-source agentic sports-data workbench — an agent team over live odds + stats: arbitrage & value detection, backtesting with CLV, monitors, racing, fantasy. BYO model key.
-
tiro
The open-source reading OS that keeps everything you read as markdown files on your machine — with a frontier-model research assistant, and your own agents, on top.
-
LeMontage
A pipeline-first workflow built for content creators: clips, reels, TikToks, shorts, podcasts and long videos. The goal is to become the TailwindCSS of content creation.
-
agent-rules-kit
Diagnose AI agent instruction files like AGENTS.md, CLAUDE.md, and Cursor rules using this local read-only Python CLI.
-
glyph
Glyph is a workbench for composing the forms intelligence takes today — and discovering the language it will speak tomorrow.
-
LedgerFrame
A private, self-hosted "wealth desk": market monitoring, portfolio & net-worth tracking, benchmarked performance analytics, world-market views, optional local voice, and grounded AI explanations — all on your own hardware. Your data stays on the device by default; nothing leaves it unless you configure it to.
-
vibestrate
Every vibe-coder needs a CTO! Let Vibestrate supervise your favorite AI models. You name the work - he makes sure it ships!
-
indexa
The local context engine for AI. Summarizes every file, rolls folders up into whole-project context, and serves any AI tool (Claude Code, Cursor, local models) a ranked slice over CLI, web & MCP. Local-first, Apache-2.0.
-
open-mind
Understand any unfamiliar codebase in an afternoon — a local, deterministic, source-traceable knowledge index (glossary · graphs · code search) that never invents what isn't there.
-
Certance-Field
Cut your GitHub Copilot token bill, locally. Certance Field compresses oversized context before it reaches the model, redacts and scans for secrets, and exports audit evidence. No cloud, no external calls.
-
memory-seed
Portable local memory system and MCP search tooling for file-reading AI coding agents.
-
hermes-agent-desktop
Automate tasks on your local machine using an AI agent client for Claude, Grok, and Gemini models on Windows, macOS, and Linux.
-
wigolo
The go-to web for your agent!
-
tinylocal-tools
Local-first browser tools for cleaning, protecting, and formatting text without uploads, accounts, analytics, or external APIs.
-
aegisloop
A guarded ChatGPT-to-Codex automation bridge for bounded local engineering loops.
-
perseus
Live context engine and MCP server for AI agents. Resolves git, services, and tests into ready context. Local-first, MIT. PyPI: perseus-ctx.
-
willow-2.0
Willow 2.0 — local-first memory, MCP tools, and fleet coordination for AI agents. Postgres KB, Ollama default, Grove LAN remote.
-
memorize
Shared, persistent memory for AI coding agents — Claude Code & Codex share one local-first, event-sourced project brain that survives sessions and syncs across machines. No server, no API key required.
-
ModelTab
No-install BYOK AI chat PWA for OpenAI-compatible, Gemini, and local/LAN LLM endpoints.
-
skill-vault
Organize, secure, and find Claude Code skills in one vault for easy reuse
-
tailor
TAILOR — self-hosted AI memory framework. 100% local, LLM-agnostic, MCP-native
-
Do-SOUL-Alaya
The local-first memory plane for CLI coding agents. Codex and Claude Code attach via MCP; SQLite-backed, evidence-gated, no GUI. Cross-session memory that the agent proposes and a governance gate decides.
-
stelekit
Local-first outliner and PKM app — plain markdown on your disk, native on every platform
-
auxly-memory-cli
A local-first, file-based memory CLI for AI tools. Own your context in plain Markdown — auditable, versionable, and provider-agnostic.
-
Yggdrasil
Durable, local-first memory for AI coding agents over MCP — zero-dependency, curated & semantically de-duped, you own the data (SQLite + Markdown). Works with Claude Code, Codex & any MCP host.
-
promptlane
PromptLane local-first prompt improvement workspace for Codex, Claude Code, and long-running coding-agent work.
-
OpenNapse
Local-first idea-to-project workspace. Capture ideas, promote to projects, plan on Kanban, link notes, track momentum — your data stays on your device.
-
resumelite
A local-first personal resume manager — keep a library of your project experiences and build tailored resumes from it.
-
digital-brain
Your private digital imprint for AI assistants.
-
@djolex999/vir-cli
An LLM Wiki for Claude Code, in your Obsidian vault.
-
napkin-ai
🧻 Knowledge system for agents. Local-first, file-based, progressively disclosed.
-
@retineo/core
Connection discovery engine (L0–L3). Open-source core for the Retineo ecosystem.
-
@swarmvaultai/engine
Core engine for SwarmVault: ingest, compile, query, lint, and provider abstractions.
-
@vpxa/aikit
Local-first AI developer toolkit — knowledge base, code analysis, context management, and developer tools for LLM agents
-
wendkeep
Automatically capture AI coding agent sessions (Claude Code, Codex) as local Markdown in your Obsidian vault — turn-by-turn history, cost/token tracking, auto-extracted decisions/bugs/learnings, rendered in the graph. Local-first.
-
neurostack
Index and search Markdown vaults as knowledge graphs to provide AI agents with persistent, structured long-term memory across sessions.
-
engineering-notebook
Capture and summarize Claude Code sessions into searchable, browsable engineering journals with a web UI and automated daily entries.
-
Bamboo-agent
Bamboo — a local-first AI agent runtime in Rust: tasks, tools, memory, MCP, workflows and schedules behind an HTTP + SSE API. The self-contained execution core powering the Bodhi desktop agent.
-
life-index
Life Index (CLI Core) — an agent-native, local-first personal life archive built on Markdown + YAML.
-
alchemical-agent-ecosystem
Build and manage local-first AI agents with real-time orchestration, dashboards, and scalable integrations using Redis, ChromaDB, and FastAPI.
-
BurnBar
Local-first macOS menu bar app for tracking AI coding agent usage, transcripts, and workflows.
-
engram
Provide your AI with persistent memory by managing past conversations across multiple sessions using simple markdown files.
-
kansei-mcp-server
Local-first MCP navigator for AI agents. 11,000+ SaaS services, 200 workflow recipes, 89-97% token savings. Works with Claude Code, Cursor, Cline, Zed, Windsurf.
-
m1nd
The shell around your coding agent: a neuro-symbolic code graph with calibrated trust, via MCP.
-
AgentsCommander
Run multiple CLI coding agents (Claude Code, Codex, Gemini, OpenCode) as a coordinated team, on a Loop. Local-first, file-based coordination, full PTY, no telemetry.
-
open-brain
Local-first search engine for your docs, knowledge bases, and notes. BM25 + vector + HyDE search over 30K+ markdown documents
-
claude-context-local
🗂️ Manage and utilize local context for Claude, enhancing applications with tailored insights and improving user experience seamlessly.
-
memcloud
☁️ Harness nearby devices to create a distributed in-memory data store, pooling RAM for fast and ephemeral storage on macOS and Linux systems.