dcode
dcode is an open-source terminal coding agent for developers and software teams. Built on the Deep Agents SDK, it can plan and execute coding tasks, inspect and edit project files, run tools, and delegate work to subagents. Its interactive terminal interface streams responses and lets users resume conversations across sessions; headless mode supports scripted and CI workflows. Users select a compatible model provider and supply their own credentials, then customize models, tools, plugins, skills, memory, middleware, hooks, and approval rules. Tool calls can be approved or rejected, and code can run locally or in supported remote sandboxes. dcode supports MCP tools and can connect to LangSmith for tracing prompts, responses, tool calls, errors, and token usage. It is intended for developers who want to configure and inspect an AI coding agent rather than use a fixed coding assistant.
Learn more about dcode
LucenaCoder
LucenaCoder is a local-first AI coding harness for software development, designed around efficient use of model context and API tokens.
LucenaCoder runs client-side by default and does not require an account. You can use the desktop application for direct filesystem access, terminal work, development servers, and long-running local tasks.
You can also run LucenaCoder from a project folder with npx lucenacoder and use the browser interface with access to your local project.
LucenaCoder supports OpenRouter and custom OpenAI-compatible endpoints, allowing you to choose your own model provider. API keys, chats, and code stay on your machine by default.
The coding agent supports SAFE and YOLO modes for different levels of filesystem and command execution access.
LucenaCoder also includes a browser-based code editor with syntax highlighting and project workspace functionality.
Learn more about LucenaCoder
Reasonix
Reasonix is an open source coding agent designed for long autonomous sessions that remain readable, auditable, and reversible. One local engine powers four interfaces: terminal, desktop app, browser, and ACP-compatible editors, with sessions, permissions, skills, and MCP servers shared across them. Plan mode holds every write until the proposed steps are reviewed and approved, while reads, writes, and shell commands are separately gated and constrained by a workspace sandbox. Each turn creates a checkpoint outside Git, allowing users to rewind a long run without affecting commit history. MCP support over stdio, SSE, and streamable HTTP merges external tools into one registry, while Markdown skills and isolated subagents extend the agent without requiring a fork. Reasonix maps a codebase once and keeps that map throughout the session, letting users queue tasks, review diffs, and resume work without losing context.
Learn more about Reasonix
Muse Code
5.0 out of 5 stars
(1 Rating)
Muse Code is Meta’s terminal coding agent, powered by Muse Spark 1.2, for handling complex software engineering tasks across large repositories. The agent can plan changes, write code, validate results, and coordinate multiple persistent subagents during development sessions. Muse Code uses async background agents that stay active throughout a session to reduce repeated information gathering and help complete multi-step tasks with less steering. Its runtime uses a local event log that records model calls, tool runs, approvals, and edits so sessions can be replayed and resumed after failures. Muse Code includes bundled skills such as /plan for approval-gated planning, /grill for stress-testing plans, and /goal for working toward completion. Built for AI developers and software teams, Muse Code helps automate coding workflows, long-running engineering tasks, debugging, and repository-level development.
Learn more about Muse Code