AgentAleph vs codeg
Local coding agents and multi-agent workspaces compared
AgentAleph is a Linux desktop app for running a coding agent with local GGUF models through llama.cpp. codeg is a multi-agent workspace for coordinating ACP-compatible agents across desktop, server, Docker, and mobile; the main difference is local-model use in a single app versus collaboration across agents and deployments.
AgentAleph: Local Coding Agent and GGUF Manager on llama.cpp
AgentAleph is a Linux desktop app built with Tauri and powered by llama.cpp for local AI coding and GGUF model management. It suits developers who want an offline-capable agent with approval-based file and command tools, without hosted inference or API keys.
codeg: Coordinate AI Coding Agents with Agent Client Protocol
Codeg is a collaborative workspace for running and coordinating AI coding agents through the Agent Client Protocol. It brings agent conversations, sessions, code changes, and tasks into one experience across desktop, self-hosted server, Docker, and mobile.
| AgentAleph | codeg | |
|---|---|---|
| Language | Rust | Rust |
| License | — | Apache-2.0 |
| Stars | 4 | 4k |
| Forks | 0 | 518 |
| Last analyzed | Oct 22, 2026 | Oct 19, 2026 |
Key differences
- AgentAleph manages GGUF models and runs inference locally through llama.cpp; codeg connects built-in and custom agents through the Agent Client Protocol.
- AgentAleph focuses on project-file tools with per-tool permissions, approval options, and read-only plan mode; codeg focuses on shared sessions, agent delegation, and parallel work in Git worktrees.
- AgentAleph documents Linux x64 as its packaged target, while codeg supports desktop, self-hosted server, Docker, iOS, and Android access.
- AgentAleph is a new beta project with limited maintenance history; codeg reports frequent commits and releases, with contribution concentrated in one person.
- Both projects use Rust; codeg specifies an Apache-2.0 license.
Choose AgentAleph if you…
- want to run a coding agent with local GGUF models without a hosted inference service or API keys.
- need approval-based file and shell tools, or a read-only planning mode for a project.
- prefer one Linux desktop app for model management and local coding work.
Choose codeg if you…
- want to coordinate several coding agents through a shared ACP-based workspace.
- need agent delegation, parallel tasks, and review of changes across sessions.
- want desktop, self-hosted, Docker, or mobile access, or a CLI for scripts and CI.
Compare the numbers side by side, or add more projects
This comparison is generated with AI from the OSRepos analyses of both projects. Always check each project's repository and documentation before choosing.