The AI agent that runs
on your machine.
217 tools. 51 skills. Self-improving. Desktop automation. Fully offline.
asyncat is a native desktop application powered by Electron. Unlike minimalist frameworks that give the model three tools and pray, asyncat dumps a context-heavy toolbox of 217 tools directly into the context window and expects the LLM to figure it out.
cd asyncat-oss && npm install
npm run electron:dev
What makes asyncat different
Controls your actual screen.
Click buttons, read text from screenshots, type into any window, focus applications. asyncat is the only open-source AI agent with real desktop automation — not just a chatbot.
Learns your workflows automatically.
The Basal Ganglia engine tracks repeated tool sequences across sessions. After 3 successful uses, it auto-generates a new skill — no annotation required. The agent gets better the more you use it.
Run risky operations safely.
Sandboxes create isolated directory copies, execute inside them, diff changes as a unified patch, and let you promote only what you want. Experiments stay isolated until you say commit.
20+ providers. Fully offline capable.
Works with OpenAI, Anthropic, Gemini, Ollama, llama.cpp, LM Studio, OpenRouter, and 13+ more. Auto-detects your GPU (CUDA, Metal, ROCm) and recommends the right runtime. No cloud required.
More than a chat box
Chain steps into automations.
Sequence agent steps into a saved workflow — each step hands its output to the next. Run it on demand or on a cron schedule, under any agent profile. The agent can trigger workflows on its own, too.
⌘K to jump anywhere.
One keystroke opens a palette to jump to any page, run a workflow, or search across your memory, notes and chats — without leaving what you are doing.
A browser the agent shares.
A real tabbed browser inside the app. Hand the agent the page you are reading with one click, or let it navigate, click and fill on its own.
Recall by meaning.
Memory and local search match on meaning, not just keywords. Uses your provider embeddings when available and falls back to a fully offline index — no cloud required.
217 tools.
Every operation an agent might need, built-in.
read · write · edit · patch · diff · watch
bash · python · node · spawn · kill · ps
clone · commit · push · branch · log · diff
browse · click · fill · screenshot · search
AST · LSP · definitions · refs · metrics
save · recall · semantic search · forget
create · list · run · history · delete jobs
list · run · multi-step · scheduled chains
markdown · HTML · diagram · CSV · PDF
build · run · stop · ps containers
create · exec · diff · patch · commit
SQL query · schema · write · CSV · JSON
describe · generate · edit images · OCR
notes · tasks · subtasks · kanban cards
sysinfo · ports · disk · network · notify
speech-to-text · text-to-speech
mail · RSS · API mapping · webhooks
Three operating modes
Chat
Conversational responses, fewer tool nudges, quick convergence. Good for research and Q&A.
Plan
Generates a structured plan without executing. Safe inspection — no mutations, no writes.
Action
Full ReAct execution loop. Runs tools, edits files, executes code. Up to 25 agent rounds.
basal-ganglia
Gets smarter
every session.
asyncat watches which tools you run, and in what order. When the same sequence succeeds three times inside a 72-hour window it stops watching and starts acting — synthesizing a new skill from the pattern and deploying it immediately.
Failures get encoded too. Corrections you make mid-run go into corrective memory, quietly shaping what the agent will avoid next time. No config, no labelling — just use it.
51 bundled skills.
Plus unlimited auto-generated skills from Basal Ganglia.
Any model. Local or cloud.
First-class integrations
Architecture
Get started in minutes.
Run natively from source or check out the pre-built installers.
cd asyncat-oss && npm install
npm run electron:dev