The Agent That
Actually Works
AI Partner is a self-hosted autonomous agent platform that researches, codes, generates documents, and delivers results to your apps — without you babysitting it.
Built different. Works different.
Human-in-the-Loop
Agent pauses before running any script. Approve or reject via Telegram inline buttons. Also handles CAPTCHA hand-off, clarifications, and mid-execution input requests.
Live Browser Automation
Full Puppeteer browser with 15fps live screencast. SPA-aware rendering, stealth mode. CAPTCHA detected? Agent pauses, you solve in the live panel, it resumes.
Sandboxed Docker Execution
Every script runs inside a persistent container with Python, Node.js, and Bash. pandas, yfinance, matplotlib pre-loaded. Network isolation per-goal.
Document Generation
PDF via Chromium, multi-sheet XLSX, PowerPoint, and DOCX — all production-ready, tracked in the dashboard, and instantly downloadable.
Skill Learning
After a successful goal, the system generalizes the solution into a reusable parameterized template. Versioned, deduplicated, and promotable to a callable tool.
Multi-Agent Delegation
Orchestrators spin up to 5 parallel sub-agents with budget controls. When a research agent exhausts its cap, it writes a handoff summary — the parent picks up seamlessly.
Scheduler + Proactive Agenda
Cron-expression tasks persist across restarts. The Proactive Agenda reads your task list and memory — uses LLM judgment to pick the best action per tick.
Vector Memory + RAG
Episodic log, vector search, persona traits, and periodic consolidation. Works with Ollama, OpenAI, Cohere, or pure-JS TF-IDF fallback — zero API keys required.
17 Built-in MCP Servers
Browser, Shell, GitHub, Gmail, Calendar, Drive, Notion, Trello, Twitter, Spotify, Apify, Image Gen, Knowledge Base, Scheduler, and more. Plus any external MCP server.
Goal in. Result out.
A 5-stage pipeline that turns natural language into validated, delivered outcomes.
Goal Extraction
Your natural-language goal is converted into a structured definition with typed, measurable success criteria — file existence, content patterns, delivery receipts — before a single action is taken.
Task Decomposition
Complex goals are broken into ordered sub-tasks with declared outputs. The right specialist agent is auto-selected by keyword or explicitly @mentioned.
Parallel Execution
Agents reason, pick tools, execute, and assess in a tight loop. Up to 5 sub-agents run in parallel. When a script fails, a semantic repair engine fixes it and retries.
Criteria-Based Validation
After every iteration the system checks real outcomes. The agent cannot self-report "done" — it's done when filesystem, content, and messaging evidence all pass.
Delivery + Checkpoint
Results delivered to Telegram, Discord, Slack, or your workspace. State is checkpointed — a restart picks up exactly where it stopped, all artifacts intact.
16 specialists. Zero generic.
What it can actually do
Criteria-Based Completion
Goals close only when real-world evidence passes — no self-reporting allowed.
Dynamic Replanning
Fails a step? Replans, tries alternatives, semantically repairs scripts, retries.
Checkpoint & Resume
State saved after each iteration. Restarts pick up exactly where they stopped.
Telegram as Control Panel
Send goals, approve scripts, receive files — all from Telegram, no UI needed.
8 LLM Providers
Anthropic, Gemini, OpenAI, Ollama, LM Studio, Groq, DeepSeek, Perplexity.
Auto-Routing
Type @handle or just a keyword — orchestrator routes to the right specialist.
Full Audit Log
Every tool call, file write, script run, and approval logged. Full run history.
Webhook + Event Triggers
Goals triggered by webhooks, Google Calendar events, or Gmail arrivals.
AI Image Generation
DALL-E 3 or Stability AI from inside any agent workflow.
Knowledge Base (RAG)
Upload PDFs, URLs — chunked, embedded, searched for grounded answers.
Security-First
URL safety checks, path guards, AES-256-GCM secrets, optional JWT auth.
Zero-Config Local Mode
Points to local Ollama by default. Start free, add keys progressively.
Connected to everything
One env var to activate any integration. Auto-discovered at startup.
Real tasks. Real outcomes.
Live Stock Portfolio Snapshot
Python + yfinance runs in Docker sandbox. Styled multi-sheet Excel with embedded chart. File criterion confirms output.
Automated Weekly GitHub Report
Scheduler fires → GitHub data fetched → report written → Slack delivery. Set once, runs forever.
Skill Learning: Instant Second Run
First run: Python from scratch. After success, system extracts a reusable template. Second run: template fills in → instant execution.
The AI That
Acts AS You
V2 transforms AI Partner from an agent INTO your AI proxy. It joins your meetings, replies to your emails, handles your calls — in your voice, with your judgment.
Watch V2 Join a Real Meeting
No scripts. No staging. AI Partner joins a live call, listens in real time, and responds.
Built for busy professionals
🎯 Entrepreneurs & Founders
Double-booked by default? AI Partner attends meetings you can't make, follows up on your behalf, monitors your market while you sleep. Your time is your revenue — stop wasting it on tasks that don't need you.
💼 Corporate CXO & Senior Leaders
Spend 6-8 hours daily in meetings most don't need your judgment — just your presence. Send the proxy. It attends, flags blockers against your OKRs, captures decisions, and reports back in minutes.
Everything V1 does. Plus this.
Human Proxy — Act AS You
AI Partner replies to your emails, Slack DMs, and Telegram messages IN YOUR VOICE. Gated by AuthorityPolicy + Telegram approvals for every action on your behalf.
Meeting Proxy — Human in the Room
AI joins your Meet/Teams/Zoom calls, listens, responds in YOUR voice (voice clone), generates summaries, and extracts action items automatically.
Proactive Heartbeat Engine
V2 doesn't wait to be asked. A background loop evaluates what to do every 15-30 minutes using your goals, memory, and real-time context.
100+ Tools, 36 MCP Servers
From 17 servers in V1 to 36 in V2. Plus 4-tier computer use (DOM → Vision → Container Desktop → Host Control) with live CAPTCHA handoff.
Phone Proxy — Voicemail + Outbound
Answer calls on your behalf. Record, transcribe, summarize. Make outbound calls using your Twilio number and YOUR TTS voice.
5-Layer Memory System
Episodic + Biographic + Counterparty + Vector + RAG. Understands who's who, what you've discussed, and maintains relationship context across all channels.
18+ LLM Providers
From 8 providers in V1. Now including NVIDIA NIM, Cerebras (~100k tokens/s), OpenRouter (100+ models), MiniMax, and LiteLLM Proxy.
Authority Policy + HITL
Declarative rules define what the agent does automatically vs. what needs your approval. Telegram inline buttons for every gray-zone decision.
V1 vs V2 — What's Changing?
V1 is live and production-ready. V2 is the next chapter.
| Capability | V1 — Available Now | V2 — Coming Soon |
|---|---|---|
| LLM Providers | 8 providers | 18+ providers including NVIDIA NIM, Cerebras |
| Tools / MCP Servers | 100+ tools, 17 servers | 100+ tools, 36 servers |
| Agent Profiles | 16 agents | ✓ Same + custom profiles |
| Human Proxy | — | Act AS you on email, Slack, Telegram |
| Meeting Join | — | ✓ Built & running — private beta Q2 2026 |
| Phone Proxy | — | Voicemail + outbound calls |
| Proactive Engine | — | Heartbeat + LLM agenda |
| Memory System | Vector + RAG | 5-layer (episodic + biographic + counterparty) |
| Computer Use | Basic browser automation | 4-tier (DOM → Vision → T3 Container → Host) |
| Skill Learning | ✓ Automatic | ✓ Enhanced + version control |
| Authority Policy | — | Per-action gating with Telegram approval |
| Self-Correction | ✓ 3-retry semantic | ✓ Enhanced with stuck detection |
Be First for V2
Secure your spot now. Early access members get first invites, exclusive onboarding, and direct founder contact.
🔥 Spots are limited — once beta fills, waitlist closes.
One command. Done.
Single Docker Compose. One API key minimum — or use local Ollama for free.
Opens at http://localhost:3000 — no config needed
Get notified when demos ship
New features, demo drops, and the public release — straight to your inbox.
🔒 No spam. Unsubscribe anytime.
Your AI partner is ready.
Are you?
Self-hosted. Local-first. No subscriptions. No cloud lock-in.