Agentty – A drop-in alternative to claude-code, written in C++26. 11.0 MB binary

Agentty, a drop-in alternative to Claude Code written in C++26, has been released as a single 11.0 MB static binary with sub-millisecond startup. The tool supports multiple AI models including Claude, GPT, Groq, and Ollama, and runs in air-gapped environments via SSH relay. It offers sandboxed execution, memory persistence, and integration with Zed through the Agent Client Protocol.

AI pair programming in your terminal One static binary. Sub-millisecond startup. Any model. curl -fsSL https://raw.githubusercontent.com/1ay1/agentty/master/install.sh | sh cd your-project agentty First launch opens auth — OAuth uses your Claude Pro/Max subscription or paste an API key. Once you're in, a first-run welcome card suggests a few things to try; just type and hit Enter. | Cold start under 1ms. No Node, no Python, no npm install. Just a static binary. Claude, GPT, Groq, OpenRouter, Ollama, or any OpenAI-compatible endpoint. Switch live with Every shell call runs inside bwrap Linux / sandbox-exec macOS . File tools refuse paths outside your workspace. | Run on a box with no internet. Your laptop relays the bytes over SSH with TLS pinned end-to-end. read · write · edit · bash · grep · glob · git · web · search docs · task — each with a purpose-built widget. Agent Skills + remember/forget memory. Teach it once, every session knows your conventions. | agentty Claude default agentty --provider openai -m gpt-4o GPT agentty --provider groq -m llama-3.3-70b Groq agentty --provider ollama -m qwen2.5-coder Local model agentty --provider openrouter Any model via OpenRouter --provider persists. Switch live in-app with ^P . | Key | Action | Key | Action | |---|---|---|---| Enter | Send | ^K | Command palette | Esc | Cancel / reject | ^J | Thread list | S-Tab | Cycle profile | ^P | Model picker | Alt+Enter | Newline | ^N | New thread | ^G | Run code block | ^←/→ or Alt+←/→ | Cycle threads | Installation options Linux Debian / Ubuntu curl -fsSLO https://github.com/1ay1/agentty/releases/latest/download/agentty amd64.deb sudo dpkg -i agentty amd64.deb Fedora / RHEL / CentOS sudo dnf install https://github.com/1ay1/agentty/releases/latest/download/agentty-x86 64.rpm openSUSE sudo zypper install https://github.com/1ay1/agentty/releases/latest/download/agentty-x86 64.rpm Arch AUR yay -S agentty-bin Alpine curl -fsSLO https://github.com/1ay1/agentty/releases/latest/download/agentty-x86 64.apk sudo apk add --allow-untrusted agentty-x86 64.apk macOS brew tap 1ay1/tap && brew install agentty Windows scoop bucket add 1ay1 https://github.com/1ay1/scoop-bucket; scoop install agentty or winget install agentty.agentty Anywhere no package manager curl -fsSL https://raw.githubusercontent.com/1ay1/agentty/master/install.sh | sh From source needs a C++26 toolchain — GCC 14+ / recent Clang / MSVC git clone --recursive git@github.com:1ay1/agentty.git cd agentty && cmake -B build && cmake --build build -j All binaries are a single fully-static executable x86 64 + aarch64 on Linux, Intel + Apple Silicon on macOS . Packaging details: packaging/README.md /1ay1/agentty/blob/master/packaging/README.md . Air-gapped hosts agentty airgap --setup user@host first time: copies credentials agentty airgap user@host every time after Your laptop relays via SOCKS5-over-SSH. TLS pins on real upstreams — the network in between can't MITM you. Inside Zed ACP agentty speaks the Agent Client Protocol https://agentclientprotocol.com — the same protocol Zed uses for Claude Code. Add to Zed's settings: { "agent servers": { "agentty": { "command": "agentty", "args": "acp" } } } Run code blocks from replies Ctrl+G The AI hands you a fenced block of commands — don't copy-paste it. ^G lists the blocks from the last reply; Enter or a digit runs one interactively on your real terminal : the TUI suspends, sudo password prompts work, output streams live, Ctrl+C kills the command not agentty . When it exits, a result card lets you attach the captured output to the composer as a collapsed chip a , copy it y , or discard Esc — so "it failed with X" reaches the model without you re-typing anything. Runs the right shell per block on every OS: sh / bash blocks through /bin/sh on Linux/macOS, powershell / pwsh and cmd / bat blocks through PowerShell / cmd.exe on Windows. Prompt $ markers are stripped, a block your platform can't run offers edit/copy instead, and capture is capped at 2 MB. Details: docs/RUN CODE BLOCK.md Agent Skills Drop a SKILL.md anywhere under .agentty/skills/ or ~/.agentty/skills/ — it's live next turn. Compatible with Claude Code's .claude/skills/ format. On codebases with internal DSLs or tribal conventions, agent accuracy jumps from ~20% to ~85% with curated skills research https://arxiv.org/abs/2410.03981 . Architecture Pure-functional update loop: Model, Msg - Model, Cmd . View is Model - Element , rendered by maya https://github.com/1ay1/maya . Process management via posix spawn + poll 2 . File writes are atomic write + fsync + rename . Deep dive: docs/ARCHITECTURE.md /1ay1/agentty/blob/master/docs/ARCHITECTURE.md · docs/RENDERING.md Releasing maintainers Cutting a release is one command: scripts/cut-release.sh X.Y.Z POSIX / macOS / Linux / Git-Bash scripts\cut-release.cmd X.Y.Z Windows cmd.exe It bumps project agentty VERSION … in CMakeLists.txt the single source of truth every manifest derives from , promotes CHANGELOG.md 's Unreleased section to X.Y.Z , commits, tags vX.Y.Z , and pushes. The tag push fires GitHub Actions, which builds every binary + OS package Linux x86 64/aarch64 on native runners, macOS Intel/ARM, Windows .exe / .msi and auto-submits to winget, Homebrew, Scoop, and the AUR — nix/snap/gentoo manifests are attached to the release. --dry-run previews without writing anything. MIT — see LICENSE /1ay1/agentty/blob/master/LICENSE .