28 boosters for "local-first" — open source, verified from GitHub, ready to install
❶ One is a new React framework - target web and native with a single Vite plugin and fully shared code, so you can ship cross-platform nearly as easy as single-platform.
"description": "Durable, fully-local project memory for Claude Code. Logs every session to .recall/history.md and condenses it into .recall/context.md with a local Python summarizer (TF-IDF + TextRank) — no API key, no external model, nothing leaves your machine. New sessions resume from the saved c
This booster helps iOS development teams systematically gather context from Linear for release impact analysis and changelog generation using hierarchical task structures. It's valuable for teams managing complex releases with multiple dependencies.
"description": "Nemp Memory — Cognitive memory layer for AI agents across every platform. Local-first, zero cloud, works with Claude, Codex, Cursor, and Windsurf.", "name": "Sukin Shetty", "email": "contact@nemp.dev",
"name": "prism-mcp-server", "mcpName": "io.github.dcostenco/prism-mcp", "description": "The Mind Palace for AI Agents — persistent memory (SQLite/Supabase), behavioral learning & IDE rules sync, multimodal VLM image captioning, pluggable LLM providers (OpenAI/Anthropic/Gemini/Ollama), OpenTelemetry
CLI tool that watches communication streams (Slack, Telegram, Discord, Linear, Gmail, Claude Code sessions, Markdown files, WhatsApp), indexes messages, detects patterns via signals, and surfaces actionable insights. Sync messages from communication sources incrementally. Hybrid search combining vec
Librarian is a local-first documentation CLI that indexes and retrieves docs using vector embeddings and SQLite, enabling developers to search and manage documentation offline with AI assistance.
"id": "ac.tandem/docs-mcp", "description": "Remote MCP server for Tandem docs, install guides, SDKs, workflows, and agent setup help.", "url": "https://github.com/frumu-ai/tandem",
"description": "🍰 Sugar - The autonomous layer for AI coding agents", "name": "Steven Leggett", "email": "contact@roboticforce.io"
Persistent local memory for AI agents. Save, recall, and search project decisions as local JSON. Zero cloud, zero infrastructure.
"mcpName": "io.github.sverklo/sverklo", "version": "0.29.2", "description": "Local-first repo-memory MCP for coding agents. Best for relationship-heavy edits: symbols, callers, dependencies, diff review, and git-pinned decisions before code changes. Start with a no-write proof receipt; use grep/ripg
Two tiers: hooks handle automatic context flow (surfacing, extraction, compaction survival). MCP tools handle explicit recall, write, and lifecycle operations. Three instances for neural inference. The wrapper defaults to . All three models auto-download via if no server is running (Metal on Appl
Read the user's memex before doing anything else. It is the current map of what is active, what changed, and where deeper evidence lives. Canonical memex path: 1. Read the memex already in context or call .
"name": "codebase-context", "description": "Pre-maps your codebase architecture, conventions, and team memory so AI agents navigate with precision instead of exploring. Local-first MCP server with AST-backed hybrid search.", "main": "./dist/lib.js",
Turn a folder of raw files into a Markdown vault that an LLM can grep, and then answer questions over that vault responsibly. source file, carrying retrieval frontmatter (abstract / tags / synonyms) + a
重点提取轨道 A（Brand）中 PPT 相关内容：Action Title 规则、版式、色值、字体。 按 references/phase-01.md ~ phase-08.md 中的详细指引执行，此处仅列阶段名称： 4. 叙事骨架搭建（Ghost Deck）
<!-- AIOS-GENERATED: orchestrator-agents v1 --> You are the Planner. Clarify scope, risks, dependencies, and execution order before code changes. Produce a concrete plan that an implementer can follow. Output a single JSON object (no surrounding text) that conforms to .
<!-- AIOS-GENERATED: orchestrator-agents v1 --> Role: security-reviewer You are the Security Reviewer. Review auth, data handling, secrets, injection risks, and unsafe automation. Do not modify code; report security findings and mitigations.
<!-- AIOS-GENERATED: orchestrator-agents v1 --> You are the Reviewer. Review correctness, regressions, maintainability, and test coverage. Do not modify code; report findings and recommendations. Output a single JSON object (no surrounding text) that conforms to .
<!-- AIOS-GENERATED: orchestrator-agents v1 --> You are the Implementer. Own code changes inside the agreed file scope and report concrete results. Prefer minimal diffs and include verification evidence. Output a single JSON object (no surrounding text) that conforms to .
A CLI skill that streamlines bug task creation in Gobby by parsing user input into structured bug reports with title, description, and priority. Useful for developers and teams using Claude Code who need rapid task logging during coding sessions.
Cortex is a local-first knowledge graph that automatically watches your project files, extracts entities and relationships using LLMs, and enables natural language queries across multiple projects. It's ideal for developers who need intelligent cross-project search and knowledge management without relying on external services.
"name": "nexo-brain", "description": "Local cognitive runtime for Claude Code \u2014 persistent memory, overnight learning, doctor diagnostics, personal scripts, recovery-aware jobs, startup preflight, and optional dashboard/power helper.", "name": "NEXO Brain",
"name": "claude-local-docs", "version": "1.0.23", "description": "Local-first Context7 alternative — indexes JS/TS dependency docs with a 4-stage RAG pipeline (vector + BM25 + RRF + cross-encoder reranking). Uses TEI Docker containers for GPU-accelerated embeddings and reranking.",
