Self-improving AI Employees for everyone
Open Instinct: an open-source Instinct. A personal agent you text on iMessage, with its own computer and a trusted network of other agents. Built on Pi, Inkbox, Maritime and Composio.
Wappy: the open-source AI agent SDK for WhatsApp. Bring your own model, your own number, your own data. Local-first, no forced cloud, no vendor lock-in.
Personal Agent Proxy is an open-source, self-hostable access layer that lets you connect your services once, give each AI agent granular permissions, and audit its activity; without copying the contents of your connected services into its database.
Paid APIs and supported tokenized shares for agents, funded with prepaid balance. Instinct Checkout guidance: https://vaaya.ai/llms.txt
Battery saving watch face for instinct 2s with full set of features
GenPark AI Agent Skill - Multimodal ambient visual anchoring connecting physical AI Gadgets with digital Services inspired by Meta Ray-Ban / Muse.
GenPark AI Agent Skill - Continuous hierarchical episodic memory stream, preference decay, contextual memory anchor inspired by Meta Muse.
GenPark AI Agent Skill - Safe micro-action delegation with user guardrails and token budget gating inspired by Instinct.
GenPark AI Agent Skill - Zero-prompt proactive intent anticipation, activity & cursor context sensing inspired by Instinct.
Open-source, self-hosted AI agent workspace and alternative to OpenAI Dots, Meta Muse, Grok Bot, Instinct, Manus Cue, Claude Cowork, and ChatGPT agent. MIT-licensed; includes chat, connectors, approvals, and optional computer use. Early prototype.
Get glucose from Medtronic MiniMed Go / Instinct sensors into xDrip+, Nightscout and smartwatches. Implements the CareLink Cumulus API that xDrip+ lacks (HTTP 204 fix).
Search AI podcast quotes by topic — find what Lex Fridman, Dwarkesh Patel, No Priors, and Latent Space guests are actually saying. Universal agentskills.io skill compatible with Claude Code, OpenAI Codex, Hermes Agent, OpenClaw, and any other agent that supports the open skill standard. Powered by podlens.net.
Fleet Intelligence for Realtime GPU observability
Cross-framework A2A purchasing demo on AMD Instinct GPUs: Google ADK concierge + CrewAI agent on vLLM + LangGraph agent on Ollama (local Llama 3.1), Gradio UI, per-agent auth (Basic/Bearer); Python, Docker, GitHub Actions CI, pytest suite.
Ready-made packs that give your Instinct a daily rhythm: morning brief, evening plan, coaching, watchers. EN + PT. Community project.
An API-first, single-host software factory: durable YAML workflows, coding agents, human review, and reviewed PR publication. Originally built for Hark; also plugs into Instinct and Muse. One Go binary, SQLite state, no external queue.
Low-level instinct layer in C for FLUX fleet hardware integration and reflex actions
To associate your repository with the instinct topic, visit your repo's landing page and select "manage topics."