Tag
Explore by tags
Self-hosted personal AI assistant reachable through 20+ messaging channels you already use — WhatsApp, Telegram, Slack, iMessage and more. A local gateway acts as the control plane, stays model-agnostic, and sandboxes tool runs via Docker or SSH.
Forecasts how social scenarios might unfold by running multi-agent simulations: thousands of LLM agents with memory and personalities, seeded from real data, that you steer by injecting variables to 'rehearse the future' in a digital sandbox.
An open large language model pairing DeepSeek Sparse Attention (DSA) for cheaper long-context inference with a scaled RL pipeline. Authors claim parity with GPT-5, with a high-compute Speciale variant surpassing it and rivaling Gemini-3.0-Pro on reasoning.
A configuration layer for the OpenCode and Codex CLI coding agents. One install adds specialized sub-agents, lifecycle hooks, and bundled MCP servers — web search, docs lookup, code search — turning a bare agent into a harness for large codebases.
Embeds Claude Code into Obsidian so a Claude-based agent can read, edit, search, and run bash inside your vault. Features include inline edits with diff previews, image analysis, slash-commands, skills/plugins, MCP integrations, and plan-mode.
On-device search engine for notes, transcripts, and code that blends BM25 full-text, vector semantic search, and a local LLM re-rank — all running offline via node-llama-cpp and SQLite. Ships an MCP server so AI agents can query your knowledge base.
Cross-platform GTD task manager for desktop, mobile, and web that covers the full Capture→Clarify→Organize→Reflect→Engage workflow with a local-first data model and flexible sync backends. Optional BYOK AI copilot and automation (CLI, REST API, MCP) help clarify and break down tasks.
Exposes models available in Kiro IDE/CLI (e.g., Claude and other provider models) as local OpenAI- and Anthropic-compatible proxy endpoints so tools and SDKs can use them. Key features: multi-account failover, streaming, tool-calling, VPN/proxy support, and Docker/Python deployments.
Generates summaries from URLs, YouTube videos, podcasts, PDFs, and local audio or video files. Backend-agnostic by design: the same pipeline drives local coding CLIs (Claude, Codex, Gemini) or hosted API providers (OpenAI, Google, xAI).
Provides a plug-and-play inference engine that lets language models programmatically inspect, decompose, and recursively call themselves to handle very long contexts; supports local and cloud REPL sandboxes, multiple LLM backends, and trajectory logging/visualization.
Fifteen reusable agent skills for curating LLM context windows, treating attention decay—not token capacity—as the real constraint. A routing layer benchmarked at 0.92 top-1 accuracy selects the right skill for each task.
Run official Claude Code/Codex/Gemini/OpenCode coding sessions locally and control them remotely via Web/PWA/Telegram — local-first workflow with seamless handoff between local and remote, AFK approvals from phone, voice assistant, and multi-agent CLI support.