Local-First Software
Discover 65 open source Local First repositories from GitHub, each with an analysis of what it does, key features, use cases and alternatives. Local First projects here are most often combined with AI Agents, Desktop App and TypeScript. Last updated October 4, 2026.
65 repositories · updated October 4, 2026
Athena-Public: Keep AI Coding Agent Context Across Sessions
Project Athena stores coding context in Markdown on your disk and uses a session routine to carry it forward between AI coding sessions. It suits developers who switch IDEs or models and want to keep their project memory portable.
agent-bridge: Connect Claude Code and Codex for Collaboration
AgentBridge relays messages between Claude Code and Codex in a shared local workflow, enabling in-session reviews and task handoffs. It is designed for developers who already use both tools and want them to coordinate without manual copy-paste.
ReMe: Manage Persistent Memory for AI Agents
ReMe turns agent conversations and resources into searchable, editable Markdown memory that can evolve over time. It suits developers building assistants that need reusable knowledge across sessions and agent runtimes.
code-review-graph: Map Code for AI Reviews
code-review-graph builds a local, persistent map of code structure and serves targeted review context to AI coding tools through MCP and a CLI. It suits teams working in large or interconnected repositories who want impact analysis without repeatedly scanning the whole codebase.
TencentDB-Agent-Memory: Share Reusable Memory Across AI Agents
TencentDB Agent Memory is a team memory hub that turns conversations, documents, and code into reusable assets for AI agents. It suits teams that want agents to share curated context and skills across sessions and frameworks.
memoripy: Build Evidence-Based Memory for AI Agents
Memoripy is a local memory runtime for AI agents that keeps versioned, sourced records and explains why they appear in recall. It suits developers who need scoped, auditable memory rather than an opaque store of accumulated text.
headroom: Compress Context for AI Agents
Headroom compresses tool outputs, logs, files, and retrieval context before they reach an LLM, helping reduce token use while retaining important details. It offers local library, proxy, and MCP integrations for agent workflows.
orbitdb: Build Peer-to-Peer Databases
OrbitDB is a JavaScript database for decentralized and local-first applications. It stores data with IPFS and synchronizes peers using Libp2p Pubsub, with Merkle-CRDTs to merge concurrent writes.
codebase-memory-mcp: Build a Searchable Code Knowledge Graph
A local MCP server that indexes repositories into a persistent graph of code structure and relationships. It helps AI coding agents answer architectural and code-navigation questions with focused queries instead of repeated file searches.
notes: Organize and Write Markdown Notes
Notes is a cross-platform desktop app for writing and organizing private Markdown notes. It combines folders, tags, a Kanban view for tasks, and a keyboard-focused editor for people who want a local note-taking workflow.
synara: Manage Coding Agents in a Desktop Workspace
Synara is a local-first desktop workspace for coordinating coding-agent sessions with project files, terminals, previews, and Git review. It suits developers who want to run locally installed agent providers and keep execution and review in one place.
cabinet: Build a Self-Hosted AI Knowledge Base
Cabinet combines a local, Markdown-based knowledge base with AI agents, scheduled jobs, and team workflows. It is aimed at people who want persistent AI context and automation while keeping their files on disk and under their control.