local-first AI agent workspace / runtime
Local-first AI agent workspace that sandboxes tool execution and records all model/tool events as an append-only log.
Same problem, same approach. Swapping one for another is a config change, not a rewrite.
Choose it for a cross-platform desktop workspace with built-in Git worktrees and multi-agent coordination.
Local-first cross-platform desktop workspace for Claude Code / agents: multi-agent, Git worktrees, code diffs, skill marketplace, multi-model, Computer Use, task-aware desktop pets, with WeChat, Feishu, DingTalk, Telegram, WhatsApp and H5 access.
Choose it for a runtime with built-in memory, credential management, and multi-model provider support.
Local-first AI agent runtime with sandboxed sessions, MCP tools, memory, credentials, audit/replay, and a built-in console. Run OpenAI, Anthropic, MiniMax, DeepSeek V4, and OpenAI-compatible models on your infrastructure.
Choose it for a lightweight model-neutral runtime with native DeepSeek/Qwen/Kimi/GLM support and MCP/skills.
Model-neutral agent desktop/runtime for private, enterprise, and OpenAI-compatible / Anthropic-compatible model API. Tested on DeepSeek, Qwen, Kimi, GLM models. Supports MCP, Skills,and local code search.
An earlier or more limited way to do the job. Still the right call when you need something small, proven, or CPU-only.
Choose it for a minimal, dependency-light agent that solves GitHub issues, no workspace UI or audit logs.
The 100 line AI agent that solves GitHub issues or helps you in your command line. Radically simple, no huge configs, no giant monorepo—but scores >74% on SWE-bench verified!
Choose it for a transparent bash-based harness when you need a simple loop without sandboxing or event logging.
Bash is all you need - A nano claude code–like 「agent harness」, built from 0 to 1
These projects were analysed and named maka among their alternatives. The relationship is not symmetric — how maka rates them is a separate judgement, made when maka is analysed in its own right.
calls maka “Use when you need an Apache-licensed workspace with append-only audit logging for agent actions.”
Open-source agentic workspace enterprises can make their own. Connect the systems you already run — 100+ integrations, MCP, chat tools, apps, browser, local files — with shared memory. Any agent (Claude Code, Codex), any model, or BYOK. Set up in clicks, not months. Local-first: your data never leaves your machines.
calls maka “Pick it for an Apache-licensed local-first agent workspace that records an append-only event log for audit.”
A multi-model AI agent desktop client — connect any AI provider, extend with MCP & skills, control from your phone. Built with Electron + Next.js.