DeepSeek-TUI
Open-source terminal agent runtime with approval modes, rollback snapshots, MCP servers, LSP diagnostics, and a headless HTTP API. Uses DeepSeek models by default.
DeepSeek-TUI is an open-source terminal UI for running a coding agent against a real local workspace. The important story is the runtime surface, not the model brand. It advertises a permission boundary (Plan, Agent, YOLO), rollback snapshots, sub-agents, MCP integration, LSP diagnostics, and background tasks with a headless HTTP and SSE interface. If you care about portability, this is a useful reference implementation for what developers now expect from a terminal agent harness: visible approvals, repeatable state, and receipts you can audit after the run.
Similar Tools
Claude Code
Anthropic's agentic coding CLI. Runs in your terminal, edits files autonomously, spawns sub-agents, and maintains memory across sessions. Powered by Claude Opus 4.
OpenAI Codex
OpenAI's coding agent for terminal, cloud, IDE, GitHub, Slack, and Linear workflows. Reads repos, edits files, runs commands, and returns reviewable diffs.
Codex CLI
OpenAI's open-source terminal coding agent built in Rust. Runs locally, reads your repo, edits files, and executes commands. Powered by o3 and o4-mini models.
Kimi Code
Open-source terminal coding agent from Moonshot AI. Powered by Kimi K2.5 (1T params, 32B active). 256K context window. Agent Swarm runs up to 100 parallel sub-agents.
Get started with DeepSeek-TUI
Open-source terminal agent runtime with approval modes, rollback snapshots, MCP servers, LSP diagnostics, and a headless HTTP API. Uses DeepSeek models by default.
Try DeepSeek-TUIGet weekly tool reviews
Honest takes on AI dev tools, frameworks, and infrastructure - delivered to your inbox.
Subscribe FreeMore AI Coding Tools
Claude Code
Anthropic's agentic coding CLI. Runs in your terminal, edits files autonomously, spawns sub-agents, and maintains memory across sessions. Powered by Claude Opus 4.
Cursor
AI-native code editor forked from VS Code. Composer mode rewrites multiple files at once. Tab autocomplete predicts your next edit. Pro plan is $20/mo.
OpenAI Codex
OpenAI's coding agent for terminal, cloud, IDE, GitHub, Slack, and Linear workflows. Reads repos, edits files, runs commands, and returns reviewable diffs.
Related Guides
Claude Code Setup Guide
Configure Claude Code for maximum productivity -- CLAUDE.md, sub-agents, MCP servers, and autonomous workflows.
AI AgentsMCP Servers Explained
What MCP servers are, how they work, and how to build your own in 5 minutes.
AI AgentsBuilding Your First MCP Server
Step-by-step guide to building an MCP server in TypeScript - from project setup to tool definitions, resource handling, testing, and deployment.
AI AgentsRelated Posts

Six More Tools for the Agent Infrastructure Stack
The second half of our agent tooling release: distribution, validation, and ergonomics layered on top of the first six....

OpenAI's GPT 5.4 in 10 Minutes
State-of-the-art computer use, steerable thinking you can redirect mid-response, and a million tokens of context. GPT 5....

DeepSeek V4 Changes the Coding Agent Cost Equation
DeepSeek V4 is trending because it is close enough to frontier coding models at a much lower token price. The real quest...

jcode and the Coding Agent Harness Wars
jcode is trending because it competes on a less glamorous but important agent metric: how cheap it is to keep many codin...

Vercel's Agentic Infrastructure Stack Explained
Vercel just declared the agent stack: AI Gateway, Sandbox, Flags, and Microfrontends. Here is how the four primitives co...

Qwen3.6-27B: A 27-Billion-Parameter Dense Model That Actually Codes
Alibaba's newest Qwen release claims flagship-level coding in a 27B dense model. Here is why dense matters, where it fit...
