Say what you need in one sentence — the agent builds the tool, tests it, and reuses it.
Every tool is sandboxed and shared with Claude Code, Codex, and any MCP agent.
curl -fsSL https://agenvoy.com/scripts/install.sh | bash
Manage sessions, tools, schedules, and memory from a browser. Open web.agenvoy.com once the daemon is running on your machine — it connects to your local agent, nothing leaves your device.
Auto-built tools and a built-in MCP server at the core — plus multi-model routing, scheduling, and memory, all in a single Go binary.
Ask for anything. If no tool exists, the agent builds one — writes the script, tests it in a sandbox, and registers it. Next time, it's already there.
Server mode shares every sandboxed tool with Claude Code, Codex, and any MCP client — which can auto-build new tools too. Client mode calls external MCP services.
10 LLM providers behind one interface. The dispatcher routes each task to the best model automatically.
Cron jobs and one-shot tasks with skill binding. Daemon fires them, hot-reloads on change, auto-disables on failure.
Context window, semantic vector search, full-text SQLite archive. Cross-session error memory with 90-day TTL.
Every command and script runs inside an OS-native sandbox — bubblewrap on Linux, sandbox-exec on macOS.
Loadable markdown instruction packs with YAML frontmatter. Slash-command activation, natural language trigger, or cron-bound.
When a skill fails, the agent rewrites it, git-commits the fix, and retries. Rollback available via git_rollback tool.
Optional KuraDB child process for external document search. Keyword + semantic dual-track over your personal knowledge base.
When no tool fits a request, the agent builds one in real-time — finds an API, writes the script, tests it, and saves it for reuse. No code required.
User asks for live data. No matching tool found.
→Search public APIs, fetch docs, pick the best match.
→Generate script + schema. Run test_tool to verify.
→Execute the new tool. Auto-persisted for all agents.
One config line gives Claude Code, Codex, and any MCP agent your entire sandboxed tool library — and they can auto-build new tools that everyone instantly shares.
Any MCP-compatible agent connects via stdio and gets access to all tools — built-in, script, API, and extension.
Connect third-party MCP servers via stdio or HTTP/SSE. Tools auto-registered and available to the agent immediately.
Same agent, same tools, same memory — accessible from terminal, chat apps, HTTP, or other AI agents.
Interactive terminal with slash commands and session switching
OTP-authenticated bot with HTML output and voice
Guild-verified bot with markdown and button confirms
OpenAI-compatible chat completions endpoint
Expose tools to Claude Code, Codex, and more
Unified Agent.Send() interface. Dispatcher auto-routes tasks to the best model.
From file ops to web search, from RAG queries to image generation. Missing a tool? The agent builds it.
Read, write, patch, list, glob, and search local files with policy guards.
Fetch pages with readability, search the web, browse news, HTTP requests.
Spawn subagents, delegate to external CLIs, run cross-reviews, plan.
Search history, persist error resolutions, query external docs via KuraDB.
Transcribe audio/video, generate images, interactive prompts, secrets.
Auto-generate tools from natural language. Drop scripts, API descriptors, or connect MCP.
One command to install, one command to start. Add a provider and you're ready.
Single binary. macOS and Linux.
curl -fsSL https://agenvoy.com/scripts/install.sh | bash
Connect any of 10 LLM providers.
agen model add
Name it. Persists across restarts.
agen session new my-agent
TUI opens. Daemon auto-starts.
agen