|
Isolade: Local-first coding agent workbench with secretless, disposable microVMs
A local-first coding agent workbench. Run Claude Code and Codex in secretless, disposable microVMs. Your code and secrets never leave your machine.
|
85 % |
|
Wedge · Sandbox for code you didn't write
Wedge runs untrusted installs, coding agents and third-party builds inside an OS sandbox that gets nothing it didn't ask for: no keys, no secret environment,...
|
85 % |
|
VisvoAI — The Python toolkit for building AI agents
One interface to any model, an agent loop done right, and a full coding agent built on both — proof it holds up. Open source, MIT licensed.
|
85 % |
|
Runvault — the secure agent shell
An agent with a real Linux shell — and the secrets locked out. Credentials stay behind a server-side proxy the sandbox never sees, and every action is logged.
|
85 % |
|
llmsnitch — Watch what your AI coding agent actually did
Local-only execution tracing for Claude Code. Every tool call your agent makes — including the file edits its permission classifier never sees — recorded to...
|
85 % |
|
Tektonix — autonomous coding agent
A self-hosted autonomous coding agent, now with a Windows app. Give it a plain-English goal and it plans the work, writes the code, runs your project's real...
|
84 % |
|
Cove — agent infrastructure
Cove runs your agent: a sandbox for every run, triggers that wake it up, scaling, and managed connectors to your tools.
|
84 % |
|
Valmis — Open-source AI agents built for work
Open-source, self-hosted AI agents that do real work without ever holding your API keys — sandboxed, proxied, with 100+ integrations and any LLM you like.
|
84 % |
|
Graphe: send in a team, not a prompt
An open-source coding agent for the desktop: helpers in parallel, a guard that asks before anything risky, and checkpoints that leave your branch and staging...
|
84 % |
|
Coban — a desktop workbench for coding agents (Codex, Claude Code, Antigravity)
Coban runs Codex, Claude Code and Antigravity on your Mac as one workbench: threads, agent teams with a Lead, review bound to the exact diff and tests, appro...
|
84 % |
|
K3 - Agent Runtime for Developers
Run Claude Code, Codex, and any supported agent in isolated workspaces with a full record of everything they did. Native desktop app for macOS, Windows, and...
|
83 % |
|
oqto - self-hosted ai agent platform
oqto - self-hosted platform for managing ai coding agents. local and container modes with web ui.
|
83 % |
|
Orkia — a shell that owns agent jobs
You're already managing agents like processes. Your tools just won't admit it. Orkia runs agents as governed Unix jobs, from any terminal.
|
83 % |
|
Orellius / Orel Ohayon
macOS apps, browser extensions, Rust cores and agent harnesses. Written solo, spec to shipped.
|
83 % |
|
kolu — the best way to run terminals
kolu is a browser terminal workspace that spans machines: point it at a box over ssh and the whole canvas runs there — terminals, code, git, agents — backed...
|
83 % |
|
silicon38 — a dynamic multi-agent organization
|
83 % |
|
EnvRelay: move your dev environment to a new machine
An Agent Skill that moves a development machine: dotfiles, credentials, git repositories, software and AI agent setup, carried in one encrypted file. You typ...
|
83 % |
|
Flightdeck
Orchestrate local AI coding agents in parallel.
|
83 % |
|
Evershell — Runtime for free agents
Your agent gets a shell. You keep the keys. A runtime for free agents.
|
83 % |
|
Agency · run coding agents locally, side by side
Agency is a free app for macOS and Linux that runs AI coding agents side by side on your own machine. Each agent gets a real terminal, its own git worktree,...
|
83 % |
Detected social media networks