Everything an agentic IDE should do — on your terms.
Autonomous agents, any model (ours, the big three, or yours), fully local when you need it, and every action you can verify.
Capuchin, the big three, or your own.
Capuchin — our model fast-and-reasoning, two tiers (Flash + Reason), tuned for coding and included in your plan.
Claude · Gemini · ChatGPT first-class via BYOK or managed; swap with a setting, not a reinstall.
Your own, local or remote Ollama/llama.cpp/vLLM on your machine, or your own server / OpenAI-compatible endpoint. Same agent features either way.
No degraded fallback local and self-hosted are full tiers, not a lesser mode.
Provider-neutral
Capuchin, the big three, or your own.
Your codebase never has to leave your machine.
On-device index Merkle-tracked, tree-sitter-chunked, embedded and searched locally.
Air-gapped mode local index + local models + internal registry. Zero outbound calls.
Optional team sync share an encrypted index when you want; turn it off and you're fully local.
Monorepo-aware a symbol/dependency graph so agents reason across services, not just nearby files.
Local-first
Your codebase never has to leave your machine.
Agents that plan, edit, run, and check.
Plan vs Fast approve a plan for complex work, or fire instant edits.
Multi-file edits coherent changes across many files, reviewed as one diff set.
Parallel sub-agents split by file cluster or service, then merged.
Real tools, gated terminal, git, test runner, browser, MCP, each behind permissions.
Agentic editing
Agents that plan, edit, run, and check.
Every agent run, signed and replayable.
Signed event logs a tamper-evident, replayable trail of plan, tools, and diffs.
Test-gated apply agents can't commit code that fails your tests.
Content-signed diffs verify exactly what changed and reproduce it byte for byte.
Audit-ready hand a run to a reviewer or compliance officer to check themselves.
Verifiable by design
Every agent run, signed and replayable.
Stop guessing your AI bill.
Included Capuchin usage generous use of our model with no per-token surprise.
BYOK frontier use Claude/Gemini/ChatGPT on your own key; we don't mark up your tokens.
Per-task budgets + hard cap agents stop instead of surprising you.
Local-first routing keep routine work near-zero cost.
Predictable economics
Stop guessing your AI bill.
The extensions you want, from a registry you can trust.
Open VSX by default vendor-neutral, legally clean for an independent IDE.
Sideload anything install any .vsix directly.
Self-hostable registry mirror and curate your own catalog.
Org governance admins set allowlists and pin versions.
Extensions, your way
The extensions you want, from a registry you can trust.
Native on all three. Same engine everywhere.
Windows · macOS · Linux signed, notarized installers; AppImage/deb/rpm/Flatpak on Linux.
One engine editor, CLI, and CI share the same core.
Background & scheduled agents long-running and cron-style, headless.
Cross-platform
Native on all three. Same engine everywhere.
Try it on your own model, on your own machine.
Download MonkeysCode and start coding with Capuchin, Claude, Gemini, ChatGPT, or your own model — free.