Results for "local-first"

A local-first personal assistant and memory harness with Obsidian integration, model routing, and automatic integration sync. GPL-3.0 licensed.

Local-first personal AI assistant with multi-channel integrations and full agentic task execution.

Local-first MCP server for explicit-budget context selection, content-addressed exact recovery, and auditable Context Receipts. Apache 2.0 licensed.

Beautiful local-first coding agent running in your terminal. Built for privacy and control with support for multiple AI providers via OpenRouter.

Local-first Expo and FastAPI Japanese practice app for Korean speakers that uses Whisper-compatible STT, local TTS, and embedding-based dialogue matching without a runtime LLM.

Local-first knowledge search engine for agents with FTS5 full-text search and graph-based document expansion via citation/support/wiki links. Pure Go, no embedding required.

Local-first workspace and harness for turning coding agents into autonomous research agents for literature review, hypothesis generation, and experiments.

Local-first desktop workbench for long-form fiction that organizes story premises, characters, worldbuilding, chapter blueprints, drafting, review, and revision, with Ollama support and Windows/macOS releases. GPL-3.0 licensed.

Local-first context and memory engine that keeps a billion-token encoded pool on disk and pages relevant slices into a small resident window for Ollama and other local LLMs. Apache 2.0 licensed.

Local-first code knowledge graph and code intelligence engine built in Golang with multi-repository support and real-time graph actualisation. Built for AI coding agents aiming to expose only the needed information, reducing token usage by up to 50x. Works natively with Claude, Codex, Hermes, and other agents.

Local-first archive and semantic search for AI conversation histories across multiple providers, with local embeddings, LanceDB storage, complete thread retrieval, HTTP and CLI access, and a stdio MCP server.

Local-first macOS AI app that runs LLM chat, image generation, voice transcription, and personal memory/RAG fully on-device via llama.cpp - nothing leaves the machine. AGPL-3.0 licensed.

Local-first desktop chat workspace where each bot runs Claude, Codex, or Grok CLI with its own thread, model, computer, connected apps, and approval flow; includes MCP and headless CLI control. Apache-2.0 licensed.

Local-first, model-agnostic environment for building, borrowing, and orchestrating specialist agents and teams across supported LLM hosts, with owner-scoped packages and host-enforced permissions. Apache 2.0 licensed.

Local-first control plane for routing coding work across Claude Code, Codex, Cursor, and OpenCode, with quota-aware rotation across multiple Claude/Codex subscription profiles, shared thread context, best-of-N runs, and cross-model review.

Local-first AI coding workspace that orchestrates multi-model planning councils, git worktrees, and task loops. MIT licensed.

Local-first voice platform for multi-engine text-to-speech, voice cloning and design, video dubbing, and dictation.

Local-first desktop workspace for coordinating AI agent teams across conversations, files, terminal, browser, Git, memory, plugins, and verification.

Workflow engine for AI where agent work is captured as reviewable .nika.yaml DAG files, statically checked before execution (schema, permits, cost floor) with tamper-evident traces after. Local-first (Ollama, llama.cpp, vLLM), MCP client and server. AGPL-3.0 licensed.

Local-first AI voice studio to clone voices, generate speech in multiple languages, and dictate text locally. MIT licensed.

Local-first web intelligence and Model Context Protocol (MCP) server for web search, crawling, and structured data extraction. AGPL-3.0 licensed.

Apache-incubating local-first AI-agent workspace with durable append-only agent execution history, licensed under Apache-2.0.

Local-first visual LLM workspace where graph edges determine the context sent to the model, with branching, merging, document extraction, and Ollama or OpenAI-compatible endpoint support. MIT licensed.

Local-first desktop multi-agent harness with persistent workspaces, capability-scoped tools, agent memory, budgets, schedules, and live runtime visualization. MIT licensed.