Skip to content
Agents tracked: 258 Downloads (7d): 219M up 9.4% GitHub stars: 5.5M VS Code installs: 148M Releases (7d): 282 Agent pull requests (last week): 940K Updated Oct 6, 2026

DeepCode by HKU Data Intelligence Lab (HKUDS)

Terminal coding agents #183 overall#28 in categoryOpen source · MIT
Pulse Score
18 / 100
Rank #183 of 258
Downloads, last 7 days
579
up 148.5% vs previous week
Downloads, last 30 days
1,738
down 12.6% vs previous 30 days
GitHub stars
16.7K
about +4 a day
Latest release
2.3.0
8d ago · 2 in 30 days
Price
Free
checked Oct 6, 2026

Overview

An open-source coding agent from HKUDS that coordinates specialised agents to turn natural-language requests and research papers into working code, with planning and verification steps; usable from the terminal, a desktop app or a web interface.

DeepCode was downloaded 579 times from PyPI in the week ending Oct 4, 2026, up 148.5% on the week before and down 12.6% over the last 30 days compared with the 30 before. The GitHub repository has 16.7K stars, 213 of them added in the last 30 days. The latest stable release is 2.3.0, published Sep 28, 2026; there were 2 stable releases in the past 30 days.

DeepCode usage and attention over time

Downloads per dayPyPI, 7-day average 83/day
GitHub starsrunning total 16.7K

Download the raw daily series: deepcode.csv

Install DeepCode

PyPIpip install deepcode-hku

These commands use the packages tracked on this page. The vendor may recommend a different installer.

Key facts

MakerHKU Data Intelligence Lab (HKUDS)
TypeOpen-source multi-agent coding framework (CLI, desktop, web)
First releasedMay 2025
LicenseMIT
Main languagePython
Open issues and PRs21

Pricing

Free and open source (MIT); users supply their own model API keys.

Source: official pricing page, checked Oct 6, 2026. Prices change often; confirm before you buy.

Pulse Score breakdown

Adoption0
Community51
Attention—
Momentum37

Each component is scored 0 to 100 from public signals; a dash means no data for it. Methodology.

DeepCode news and signals

All AI agent news

  1. New on AgentGid AgentGid

    101 agents added to AgentGid

    DeepSeek Harness, CopilotKit, Orca, eve, ARTEMIS, Jasper, Harvey, Paradox, Eightfold AI Interviewer, TesterArmy e2e, Copy.ai, Consensus and 89 more

  2. Release GitHub Releases

    DeepCode 2.3.0 released

    One local service, three interfaces. deepcode, deepcode desktop, and the new deepcode web all connect to the same local background service. Closing a client leaves running work in the background;…; Dictate your prompt. Add a dictation block to your config…

What changed: recent DeepCode releases

5 stable releases in the last 90 days · Full changelog

2.3.0
  • One local service, three interfaces. deepcode, deepcode desktop, and the new deepcode web all connect to the same local background service. Closing a client leaves running work in the background;…
  • Dictate your prompt. Add a dictation block to your config and the Desktop and Web composer gains a microphone. Speech is transcribed by a Parakeet server or the local parakeet-mlx command and…
  • More providers, truer numbers. Opper (one EU-hosted, OpenAI-compatible key for many vendors) and Amazon Bedrock join the templates, and DeepSeek V4 models use their own 1M-token window and pricing…
  • Desktop polish. Drag the conversation's edge to resize it, import a VS Code color theme, and pick from fonts that are actually installed. (#238, #207,
  • Opt-in hardening for relayed model traffic. providers.egress limits which hosts receive your prompts; DEEPCODECOMMANDSCREEN=strict refuses piped remote scripts, unknown package indexes, and…
  • Leaner memory, clearer signals. MEMORY.md can be a short index of topic files that the agent reads on demand, kept deduplicated and within budget; mcp list flags servers worth a second look; the…
2.2.0
  • Sessions that hold up. Resuming a session restores what the agent did, not only what it said; compaction keeps the recent tail and can be triggered on demand with /compact; context pressure is…
  • Your models, declared. A dsh-style settings dialog with per-model declarations (context window, capacities, reasoning ladder), live model discovery per connection, a Session-level context-window…
  • A terminal that reads like an app. Every bare command opens a selector, the TUI has a status line and tool cards, and a new turn no longer discards the prompt cache.
  • Sub-agents and MCP, on demand. Delegate to Codex or Claude Code as sub-agents, hold follow-up conversations with native ones, activate MCP servers lazily, and let hooks see the whole lifecycle…
  • Memory with boundaries. Compaction leaves a note in workspace memory, and injected memory content sits inside an escaped <untrusted-data> boundary, so a poisoned note cannot forge instructions.
  • Desktop in Simplified Chinese, eight themes including a high-contrast one, an appearance scale that actually resizes the app, and a project switch that no longer strands the MCP catalog.
2.1.0
  • chore: land PRs #139/#148/#149 with original authorship
  • Revert Windows private-file ACL restriction (broke main)
  • docs: add CONTRIBUTORS.md
  • fix: import LoopDetector, ProgressTracker
  • fix: surface detailed workflow errors in the UI
  • fix(backend): prevent path traversal in SPA catch-all route
2.0.0
  • ⏸️ Complex tasks stop halfway and require repeated prompts to continue
  • 🧪 Code appears complete, but tests, builds, and runtime behavior are not actually verified
  • 🔁 Regression checks, test repairs, documentation updates, and repository maintenance must be initiated manually each time
  • 🔄 Loop Engineering
  • 🎛️ Control throughout execution
  • ✅ Verified delivery
1.3.0
  • 统一 CLI、Web 与 Headless 模式的 Agent 内核和事件协议,同时保留原有 Paper2Code 工作流。
  • 新增交互式 CLI、原生编程工具、持久化 Session、项目记忆与长对话上下文管理。
  • 引入权限控制、安全沙箱、工具审批及工作区隔离机制。
  • 支持自主循环、定时任务、并行团队与模型驱动的子代理协作。
  • 支持 Skills、生命周期 Hooks、分层配置,以及在任意目录中启动和恢复 DeepCode。
  • Unified the agent runtime and event protocol across CLI, Web, and headless modes while preserving the existing Paper2Code workflow.
1.2.0
  • 本次更新主要包括: DeepCode + nanobot 集成:支持通过 飞书机器人 调用 DeepCode,在聊天中发起论文转代码、对话转代码和任务进度查询,并新增飞书实战截图示例。 文档重构:全面更新 README.md 与 READMEZH.md,优化 Quick Start 结构,新增 nanobot 集成(飞书聊天机器人) 专章,并提供从配置到部署的一站式教程。…
  • This release focuses on better chat-based usage and documentation: DeepCode + nanobot integration: You can now use DeepCode directly from a Feishu bot, including paper-to-code, chat-to-code, and…

DeepCode alternatives

All terminal coding agents

# Agent Pulse Downloads 7d 7d 30d VS Code installs Stars Latest release Price Last 90 days
1 83 25.6M up 5.7% up 21.2% 15.2M 128K+153/day 0.160.1yesterday Free + $8/mo
3
Claude CodeAnthropic
80 14.8M up 11.6% down 36.4% 27.1M 150K+161/day 2.1.290yesterday $20/mo
5
PiEarendil Inc. (created by Mario Zechner)
75 5.2M up 29.8% up 52.1% — 113K+378/day 1.0.4yesterday Free (OSS)
7
OpenCodeAnomaly (SST team)
73 3.3M up 22.0% up 6.1% 1.2M 212K+200/day 1.18.346d ago Free + $10/mo
25 57 453K up 4.7% up 1.8% 1.1M 107K+24/day 0.62.07d ago Varies
28
Oh My PiStencil Labs (Can Bölük)
56 241K up 11.4% up 53.9% — 34.4K+111/day 18.6.12d ago Free (OSS)

DeepCode FAQ

How much does DeepCode cost?

Free and open source (MIT); users supply their own model API keys.

Is DeepCode open source?

Yes. DeepCode is open source, released under the MIT license.

How popular is DeepCode?

DeepCode was downloaded 579 times from PyPI in the week ending Oct 4, 2026, up 148.5% on the week before and down 12.6% over the last 30 days compared with the 30 before. The GitHub repository has 16.7K stars, 213 of them added in the last 30 days. The latest stable release is 2.3.0, published Sep 28, 2026; there were 2 stable releases in the past 30 days.

What is the latest version of DeepCode?

The latest stable release we track is 2.3.0, published on Sep 28, 2026.

What are the alternatives to DeepCode?

The closest alternatives in the same category by Pulse Score are OpenAI Codex, Claude Code, Pi, OpenCode.

Where these numbers come from

PyPI: deepcode-hku. GitHub: hkuds/deepcode. See data sources for how each one is collected.

Product facts and pricing were checked against: github.com, pypi.org.