The agent that grows with you

Not a chatbot. An autonomous agent with persistent memory, self-improving skills, and the ability to run anywhere. 100% free and open source.

Never forget context again

Persistent Memory

Agent-curated memory with periodic nudges, FTS5 cross-session recall with LLM summarization. It remembers everything and builds a deepening model of who you are.

Gets smarter over time

Self-Improving Skills

Autonomous skill creation from experience, self-improvement during use. Skills are portable, shareable, and community-contributed via the Skills Hub.

From $5 VPS to GPU clusters

Runs Anywhere

6 terminal backends: local, Docker, SSH, Daytona, Singularity, Modal. Daytona and Modal offer serverless persistence — your environment hibernates when idle, costing nearly nothing.

Control from anywhere

20+ Messaging Platforms

CLI, Telegram, Discord, Slack, WhatsApp, Signal, Matrix, Mattermost, Email, SMS, Microsoft Teams, Google Chat, and more — all from one unified gateway.

Works while you sleep

Scheduled Automations

Built-in cron with delivery to any platform. Set up recurring tasks that run while you sleep and report results where you want them.

Parallel execution

Subagent Delegation

Spawn isolated subagents for parallel workstreams. Programmatic Tool Calling via execute_code collapses multi-step pipelines into single inference calls.

Everything you need

70+ Built-in Tools

Web search, browsing, extraction, vision, image generation, TTS, code execution, file operations, git, databases, and more. All configurable.

Extensible architecture

MCP Integration

Connect to any Model Context Protocol server for extended tool capabilities. Filter tools, sandbox access, extend safely.

Hands-free operation

Voice Mode

Real-time voice interaction in CLI, Telegram, and Discord. Whisper transcription, multiple TTS providers. Talk to your agent naturally.

Safe autonomous operation

Enterprise Security

Command approval workflows, user authorization across platforms, container isolation for code execution, resource limits.

Your choice of models

Any LLM Provider

Ollama (local), OpenAI, Anthropic, Groq, OpenRouter, and more. Use local models for free and private operation, or cloud for maximum capability.

Free forever

100% Open Source

MIT licensed. No cloud required. No subscriptions. No API costs if you use local models. Full source code. You own everything.

Why Quill-Agent?

FeatureQuill-AgentChatGPTOther Agents
Persistent MemoryYesNoSome
Self-Improving SkillsYesNoNo
Local ExecutionYesNoSome
20+ Messaging PlatformsYesNoNo
100% FreeYesNoSome
Open SourceYesNoSome
No API CostsYesNoNo
Scheduled AutomationsYesNoSome

Ready to get started?

Install in 60 seconds. Run locally with no API costs. Start building the agent that grows with you.