Skip to content
Agentmart
Submit a tool

dscode

Local-first MIT coding agent with DeepSeek defaults, provider switching, OS sandboxing and a checkpoint for every patch.

Agent by thinkany-ai

IndexedMIT★ 365
Write a review

Chalk Labs

Need help deploying dscode?

Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.

Book a call

Get started

Setup steps are in the repository. Website · Repository

About

DSCode is a local coding-agent runtime that uses DeepSeek V4 Flash as its default model and can switch to Codex, OpenAI, Anthropic, OpenRouter, Z.AI, Kimi, MiniMax, xAI or OpenCode Zen Go through /login. It runs explorer, implementer, reviewer and tester roles in parallel, with implementers working in isolated Git worktrees. Commands run in an OS sandbox with network blocked by default, sessions are stored as local JSONL, and every successful patch creates a checkpoint. The README says the macOS desktop builds are notarized and the Windows and Linux builds are unsigned.

Use cases: coding, testing, code-generation, code-review

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Fact sheet

Jobs
coding, testingREADME
Where you use it
Terminal, Desktop app, IDEREADME
Hosting
You run itREADME
Models
deepseek, openai, anthropic, openrouter, xai, kimi, minimaxREADME
Interfaces
mcp, agent-skillsREADME
Open source
YesREADME
Billing
The /status command reports context, cache hits, tokens and estimated cost for each session.README

Facts extracted by Claude Haiku 5.5 from the linked sources on Oct 24, 2026. Wrong fact? Tell us.

Built on

Frameworks named in its dependency files.

Signals

Stars
365
Forks
39
Open issues
0
Last commit
Sep 30, 2026 (1 month ago)
Last release
Aug 13, 2026 (2 months ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
Website
dscode.ai
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

Done for you

Rather not set it up yourself?

Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.

See how we build AI agents →Read the case studies

Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.

launches shipped
50+
launches shipped
media placements
500+
media placements
founders on every account
2
founders on every account

Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block

Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.

Get dscode running in your business

Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.

Goes to the Chalk Labs founders, not the newsletter. Privacy

Need help deploying dscode?

CallGet help
Cite this page

dscode. Agent Mart. https://agentmart.dev/agents/dscode-313d1d (last updated 2026-10-24)