AI CLIs & agents · HKUDS · ↗ Trending on GitHub

DeepCode changelog

"DeepCode: Open Agentic Coding (Agent Harness & Loop Engineering & Multi-Agent Orchestration)"

Latest version
v2.3.1
Last shipped
7d ago
GitHub stars
17k +7/wk
Avg. release gap
31.7 days
Weekly activity · last 26 weeks0 updates · 25w ago0 updates · 24w ago0 updates · 23w ago0 updates · 22w ago0 updates · 21w ago0 updates · 20w ago0 updates · 19w ago0 updates · 18w ago0 updates · 17w ago0 updates · 16w ago0 updates · 15w ago0 updates · 14w ago1 update · 13w ago0 updates · 12w ago0 updates · 11w ago1 update · 10w ago1 update · 9w ago0 updates · 8w ago0 updates · 7w ago1 update · 6w ago0 updates · 5w ago0 updates · 4w ago1 update · 3w ago0 updates · 2w ago1 update · 1w ago0 updates · this week

Release history

Recent updates

Monday, October 12Oct 12, 2026

Release v2.3.1

DeepCode v2.3.1

DeepCode v2.3.1 is a stability release for the terminal UI on the shared background service. Answers now appear once and render as Markdown while they stream, the TUI survives a slow or restarted service, /compact works on coding sessions, and the background…

Read full notes

DeepCode v2.3.1 is a stability release for the terminal UI on the shared background service. Answers now appear once and render as Markdown while they stream, the TUI survives a slow or restarted service, /compact works on coding sessions, and the background service no longer stops right after starting on Windows installs in a virtual environment. It also includes five community fixes and dependency security updates.

Highlights

  • Answers shown once, rendered as Markdown. The TUI no longer prints an answer a second time when it finishes, and a stopped answer keeps the text already shown. Headings, lists, bold text and tables are formatted as each line completes; code blocks are not indented or wrapped by DeepCode, so they copy back exactly; links show their address; and the line still being written is previewed above the status line. /raw prints answers exactly as written. The reasoning card comes before the answer, Ctrl+O mid-answer no longer repeats or drops lines, and text such as root:x:0 or :smile: is no longer turned into emoji. See The terminal UI.
  • A TUI that keeps working. A failed request, an unrenderable event, or a restarted service no longer closes the TUI; /reconnect starts the service again when needed. Typing, completion, Enter and Ctrl+C stay responsive while the service is busy, and a slow answer is reported instead of retried three times. Esc interrupts only from an empty prompt and Ctrl+C first clears your draft, so a message you are typing is never lost or sent by accident.
  • Settings that stay current. Default model and access changes show up in the TUI, /new follows your defaults, an approval answered in another client is announced, and /goal clear out … sets a new objective instead of clearing the Goal.
  • /compact that works on coding sessions. Compaction runs in its Session's turn, so a message sent meanwhile waits for the summary and the next reply does not start with a failed request. Tool-call arguments, such as the file a write_file call carries, now count, so a session that wrote large files compacts instead of being refused as "would not shrink". A refusal says why. (#258)
  • The Windows service stays up. On a Windows install in a virtual environment, the background service stopped right after it reported ready, whichever of the TUI, deepcode service start, or deepcode web launched it. It now stays up.
  • Community fixes. Diff lines that contain a Unicode line separator or a form feed stay whole (#253); web fetch refuses private addresses tunnelled through NAT64 or IPv4-compatible IPv6 (#254); the destructive-command screen also catches absolute paths such as /bin/rm -rf / (#255); and glob finds files when the project sits under a directory named build or venv (#256).
  • Security updates. pypdf, PyJWT, urllib3, and multidict move to patched releases.

Upgrading

pip install -U deepcode-hku, then deepcode service restart so the background service runs the new version. The TUI tells you when the client and the service versions differ.

Thanks

This release includes contributions from @KennyMcSimpson, @raymondginger2018-sudo, @D41910, and @liuzhengyang699, and @raymondginger2018-sudo and @rifkir23 tracked down the cause of the failing Windows CI job. Thank you.

Full changelog: https://github.com/HKUDS/DeepCode/compare/v2.3.0...v2.3.1


DeepCode v2.3.1 是一次针对共享后台服务下终端界面的稳定性更新:回答只显示一次,并且边输出边渲染成 Markdown;后台服务变慢或重启时 TUI 照常工作;/compact 能压缩写代码的会话;在 Windows 上把 DeepCode 装在虚拟环境里时,后台服务不再刚启动就退出。本版本还包含五项社区修复和依赖的安全更新。

亮点

  • 回答只显示一次,并渲染成 Markdown。 回答结束时,TUI 不再把整段重新打印一遍;被中断的回答会保留已经输出的文字。标题、列表、粗体和表格在每行写完时排好;代码块不缩进,DeepCode 也不会给它折行,复制出来和原文一致;链接显示完整地址;还没写完的那一行先在状态行上方预览。/raw 按原文输出。推理卡片显示在回答之前;回答途中按 Ctrl+O 不会再重复或丢行;root:x:0、:smile: 这类文字不再被替换成表情。参见终端界面指南(英文)。
  • TUI 不再轻易中断。 请求失败、遇到无法显示的事件、后台服务重启,都不会再让 TUI 退出;需要时 /reconnect 会重新启动后台服务。服务忙时,打字、补全、Enter 和 Ctrl+C 照常响应;回答慢时会直接说明,不再连续重试三次。只有输入框为空时 Esc 才中断回合,Ctrl+C 先清空正在输入的内容,正在写的消息不会丢失,也不会被误发。
  • 设置及时生效。 修改默认模型或权限后,TUI 会显示最新值;/new 跟随默认设置;在其他客户端处理过的审批会有提示;/goal clear out … 会设为新目标,而不是清掉当前 Goal。
  • /compact 能压缩写代码的会话。 压缩在会话自己的回合里进行,期间发来的消息会等摘要完成,压缩后的第一次回答不再先失败一次。工具调用的参数(比如 write_file 写入的整个文件)也会计入,写过大文件的会话不再被判成"压缩后不会变小"而拒绝。被拒绝时会说明原因。(#258)
  • Windows 后台服务不再自行退出。 在 Windows 上把 DeepCode 装在虚拟环境里时,后台服务报告就绪后随即退出,无论是由 TUI、deepcode service start 还是 deepcode web 启动。现在能正常运行。
  • 社区修复。 含 Unicode 行分隔符或换页符的行在 diff 里不再被拆开(#253);网页抓取会拒绝经 NAT64 或 IPv4 兼容 IPv6 地址访问内网(#254);危险命令筛查也能识别 /bin/rm -rf / 这类绝对路径写法(#255);项目放在名为 build 或 venv 的目录下时,glob 也能找到文件(#256)。
  • 安全更新。 pypdf、PyJWT、urllib3、multidict 升级到修补版本。

升级

pip install -U deepcode-hku,然后运行 deepcode service restart,让后台服务也换成新版本。客户端与后台服务版本不一致时,TUI 会提示。

致谢

本版本包含来自 @KennyMcSimpson、@raymondginger2018-sudo、@D41910 与 @liuzhengyang699 的贡献;@raymondginger2018-sudo 和 @rifkir23 还查明了 Windows CI 失败的原因。谢谢你们。

Monday, September 28Sep 28, 2026

Release v2.3.0

DeepCode v2.3.0

DeepCode v2.3.0 runs the TUI, Desktop, and a new browser client on one local background service, so work you start in one interface keeps running and can be followed and approved from another. It adds voice dictation, Opper and Amazon Bedrock, correct DeepSeek…

Read full notes

DeepCode v2.3.0 runs the TUI, Desktop, and a new browser client on one local background service, so work you start in one interface keeps running and can be followed and approved from another. It adds voice dictation, Opper and Amazon Bedrock, correct DeepSeek V4 numbers, and a set of opt-in protections for model traffic that passes through a relay. It also fixes a SQLite locking bug behind occasional "database disk image is malformed" errors and folds in three weeks of community work.

Highlights

  • 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; reconnect from another interface to follow the conversation and answer approvals. Model connections you save work in all three, and you can test streaming and tool calls before relying on a custom server. Manage the service with deepcode service. (#212)
  • 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 inserted at the cursor for you to review. (#240)
  • 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 instead of V3's. (#242, #208, #249)
  • 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, #239)
  • Opt-in hardening for relayed model traffic. providers.egress limits which hosts receive your prompts; DEEPCODE_COMMAND_SCREEN=strict refuses piped remote scripts, unknown package indexes, and look-alike package names; DEEPCODE_BASH_SCRUB_ENV=1 keeps provider keys out of shell commands; DEEPCODE_TRANSPARENCY_LOG=1 makes the LLM log tamper-evident; DEEPCODE_KEYRING=1 reads keys from the OS keychain. All are off by default. The legacy command executor now applies the destructive-command screen as well, and each session logs its resolved permission posture. (#228–#232, #246)
  • 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 agent gets a one-time reminder when a call keeps returning the same result; a misspelled tool name gets a "did you mean"; python -m core.observability.llmops summarizes cost and latency; and schedules can skip the model call when nothing they watch has changed. (#233, #241, #247, #215, #221, #227)
  • Steadier everywhere. The state database no longer drops its SQLite locks when several DeepCode processes share it; the memory data boundary now catches every spelling of its closing tag; and Windows fixes landed for GBK consoles, .git/info/exclude, private-storage permissions, and the entry point. (#243, #210, #237, #235, #236)

Upgrading

pip install -U deepcode-hku. From this release on, deepcode service prepare-upgrade --output <path> stops the background service and snapshots its state before an upgrade; see Upgrading DeepCode.

Thanks

This release includes contributions from @Dev-next-gen, @EduCosta85, @Felixkw12, @lihuiyang1024, and @raymondginger2018-sudo — thank you.

Full changelog: https://github.com/HKUDS/DeepCode/compare/v2.2.0...v2.3.0


DeepCode v2.3.0 让 TUI、Desktop 和新增的浏览器客户端共用一个本地后台服务:在一个界面里开始的任务会在后台继续运行,并能在另一个界面里跟进和审批。本版本新增语音输入、Opper 与 Amazon Bedrock 模板、正确的 DeepSeek V4 参数,以及一组针对经过中转的模型流量、需要主动开启的防护。它还修复了一个 SQLite 锁的问题(此前偶发"database disk image is malformed"错误的原因),并合入了三周来的社区贡献。

亮点

  • 一个本地服务,三种界面。 deepcode、deepcode desktop 与新增的 deepcode web 都连接同一个本地后台服务。关闭客户端后,正在运行的工作留在后台;从另一个界面重新连接,即可继续跟进对话、回应审批。保存的模型连接在三种界面通用,使用自定义服务前可以先测试流式输出与工具调用。用 deepcode service 管理后台服务。(#212)
  • 用语音输入提示词。 在配置中加入 dictation 后,Desktop 与 Web 的输入框会出现麦克风。语音由 Parakeet 服务或本地 parakeet-mlx 命令转写,插入到光标处,发送前可以检查修改。(#240)
  • 更多服务商,更准的参数。 新增 Opper(用一个托管在欧盟的 OpenAI-compatible 密钥调用多家厂商的模型)与 Amazon Bedrock 模板;DeepSeek V4 使用自己的 100 万上下文与价格,不再沿用 V3 的数值。(#242、#208、#249)
  • Desktop 细节打磨。 拖动会话区边缘即可调宽,可以导入 VS Code 配色主题,字体选择只列出本机已安装的字体。(#238、#207、#239)
  • 可选的中转流量加固。 providers.egress 限定哪些主机能收到你的提示词;DEEPCODE_COMMAND_SCREEN=strict 拒绝下载后直接执行的远程脚本、未知的包索引和仿冒包名;DEEPCODE_BASH_SCRUB_ENV=1 不把服务商密钥交给 shell 命令;DEEPCODE_TRANSPARENCY_LOG=1 让 LLM 日志可以校验是否被篡改;DEEPCODE_KEYRING=1 从系统钥匙串读取密钥。以上默认全部关闭。另外,旧版命令执行器也会先经过危险命令筛查,每个 Session 会在日志里记录最终生效的权限状态。(#228–#232、#246)
  • 更轻的记忆,更清楚的提示。 MEMORY.md 可以只是一份主题文件索引,由 Agent 按需读取,并保持去重、不超预算;mcp list 会标出值得再看一眼的 server;同一调用反复返回相同结果时,Agent 会收到一次提醒;工具名写错时会提示"是否想用";python -m core.observability.llmops 汇总成本与延迟;定时任务在监视的内容没有变化时可以跳过模型调用。(#233、#241、#247、#215、#221、#227)
  • 各平台更稳定。 多个 DeepCode 进程共用状态数据库时不再丢失 SQLite 锁;记忆的数据边界能识别结束标签的各种写法;Windows 上修复了 GBK 控制台、.git/info/exclude、私有存储权限与入口文件的问题。(#243、#210、#237、#235、#236)

升级

pip install -U deepcode-hku。从本版本起,升级前可以用 deepcode service prepare-upgrade --output <路径> 停下后台服务并为状态做快照,详见升级指南(英文)。

致谢

本版本包含来自 @Dev-next-gen、@EduCosta85、@Felixkw12、@lihuiyang1024 与 @raymondginger2018-sudo 的贡献——谢谢你们。

Sunday, September 6Sep 6, 2026

Release v2.2.0

DeepCode v2.2.0

DeepCode v2.2.0 makes long sessions dependable and puts the model under your control: sessions survive resume, compaction, and a second window; settings, models, and reasoning are declared rather than guessed; sub-agents and MCP servers start when needed and…

Read full notes

DeepCode v2.2.0 makes long sessions dependable and puts the model under your control: sessions survive resume, compaction, and a second window; settings, models, and reasoning are declared rather than guessed; sub-agents and MCP servers start when needed and stop cleanly; and the Desktop speaks Simplified Chinese. It also folds in a month of community fixes and security hardening.

Highlights

  • 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 measured from the provider's own usage; and two windows on one session no longer crash each other — one live writer per session, enforced.
  • 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 cap (/context 64k), and keys that reach exactly the requests they were resolved for.
  • 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 (SessionEnd, PreCompact).
  • 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.
  • Hardening. Command-executor bypasses closed, native file operations routed through the sandbox, Windows private files protected by a fail-safe ACL, Plugin manifests warned about plaintext credentials, and dependency advisories (pip, pypdf, browserslist) cleared.

Thanks

This release includes contributions from @atirna, @lihuiyang1024, @rifkir23, @MarkHe1222, @imshunsuke, and @raymondginger2018-sudo — thank you.

Full changelog: https://github.com/HKUDS/DeepCode/compare/v2.1.0...v2.2.0


DeepCode v2.2.0 让长会话变得可靠,并把模型真正交到你手里:Session 经得住恢复、压缩和第二个窗口;设置、模型与推理档位改为显式声明而非猜测;子代理与 MCP 服务器按需启动、干净退出;Desktop 说简体中文。同时合入了一个月的社区修复与安全加固。

亮点

  • 站得住的 Session。 恢复会话时找回的是 Agent 做过什么而不只是说过什么;压缩保留最近的尾部,也可用 /compact 按需触发;上下文压力按服务商报告的真实用量测量;同一 Session 开两个窗口不再互相崩溃——每个 Session 只有一个活跃写入者,由系统锁保证。
  • 你的模型,显式声明。 dsh 风格的设置对话框,逐模型声明(上下文窗口、容量、推理档位),每个连接可实时发现模型,Session 级上下文上限(/context 64k),密钥只到达为它解析的请求。
  • 像应用而不是日志的终端。 每个裸命令都打开选择器,TUI 有状态行与工具卡片,新的 Turn 不再丢掉提示缓存。
  • 按需的子代理与 MCP。 可把任务委派给 Codex 或 Claude Code 子代理,与原生子代理进行后续对话,MCP 服务器懒启动,Hooks 看得到完整生命周期(SessionEnd、PreCompact)。
  • 有边界的记忆。 压缩会在工作区记忆里留下一条笔记;注入的记忆内容包在转义过的 <untrusted-data> 边界里,被投毒的笔记无法伪造指令。
  • 简体中文的 Desktop,八套主题(含高对比度),真正缩放整个应用的字号偏好,以及切换项目不再让 MCP 目录卡住。
  • 安全加固。 堵上命令执行器的绕过,原生文件操作走沙箱,Windows 私有文件获得 fail-safe 的 ACL,插件清单对明文凭据发出警告,并清除了 pip、pypdf、browserslist 的依赖公告。

致谢

本版本包含来自 @atirna、@lihuiyang1024、@rifkir23、@MarkHe1222、@imshunsuke 与 @raymondginger2018-sudo 的贡献——谢谢你们。

Wednesday, August 12Aug 12, 2026

Release v2.1.0

DeepCode v2.1.0

DeepCode v2.1.0 unifies Skills, Agent Plugins, and MCP across CLI, TUI, and Desktop. It includes reviewed upstream Skills, a managed MCP catalog with OAuth and real connection tests, portable local Plugins, and verified packaged-runtime resources. What's…

Read full notes

DeepCode v2.1.0 unifies Skills, Agent Plugins, and MCP across CLI, TUI, and Desktop. It includes reviewed upstream Skills, a managed MCP catalog with OAuth and real connection tests, portable local Plugins, and verified packaged-runtime resources.

What's Changed

New Contributors

Full Changelog: https://github.com/HKUDS/DeepCode/compare/v2.0.0...v2.1.0

Monday, August 3Aug 3, 2026

Release v2.0.0

DeepCode v2.0.0

After continuous iteration, HKUDS DeepCode v2 is officially released 🚀 An open-source, general-purpose Coding Agent built for real-world software engineering. Coding Agents are becoming increasingly capable of generating high-quality code. However, developers…

Read full notes

After continuous iteration, HKUDS DeepCode v2 is officially released 🚀 An open-source, general-purpose Coding Agent built for real-world software engineering.

Coding Agents are becoming increasingly capable of generating high-quality code. However, developers still face several recurring problems in real projects:

  • ⏸️ 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

DeepCode v2 is designed to reduce this repeated communication and manual work.

Instead of only generating code, it helps developers continuously move tasks forward inside real repositories until the results are verified and ready for review.

What is new in DeepCode v2:

  • 🔄 Loop Engineering DeepCode continuously understands, implements, verifies, and repairs work around a natural-language Goal. It does not stop after producing a single response, but keeps progressing based on real execution results.

  • 🎛️ Control throughout execution Developers can add requirements, revise the Goal, pause, resume, or change direction while the Agent is running, without losing work that has already been completed.

  • ✅ Verified delivery DeepCode actually runs commands, tests, and builds, and delivers results together with code changes and execution evidence, making them easier to review, validate, and merge.

  • 🤖 Personalized Automation Developers can create project-specific tasks using natural language and run them manually or on a schedule for regression checks, test repairs, documentation synchronization, and repository maintenance.

  • 💻 Unified CLI and Desktop experience The same project, Session, Goal, and execution history can be continued across both CLI and Desktop, reducing context loss when switching tools.

We hope DeepCode v2 helps open-source developers and engineering teams spend more time on meaningful design, decision-making, and creation—and less time repeatedly prompting Agents, rechecking results, or explaining the same task again.

Less prompting. More completed work.

Try DeepCode v2, share your feedback, open an Issue, or join us in building it together. 🚀

Friday, July 17Jul 17, 2026

Release v1.3.0

DeepCode v1.3.0

DeepCode v1.3.0 完成了 V2 架构升级,将 DeepCode 扩展为更统一、安全且可扩展的通用智能编程代理。 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…

Read full notes

DeepCode v1.3.0 完成了 V2 架构升级,将 DeepCode 扩展为更统一、安全且可扩展的通用智能编程代理。

  • 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。

DeepCode v1.3.0 delivers the V2 architecture upgrade, evolving DeepCode into a more unified, secure, and extensible general-purpose coding agent.

  • Unified the agent runtime and event protocol across CLI, Web, and headless modes while preserving the existing Paper2Code workflow.
  • Added an interactive CLI, native coding tools, persistent sessions, project memory, and long-context management.
  • Introduced permission controls, security sandboxing, tool approvals, and workspace isolation.
  • Added autonomous loops, scheduled tasks, parallel teams, and model-driven subagent collaboration.
  • Added Skills, lifecycle Hooks, layered configuration, and support for launching and resuming DeepCode from any directory.

Wednesday, February 11Feb 11, 2026

Release v1.2.0

DeepCode v1.2.0

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 README_ZH.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。 此版本重点提升了“在聊天软件中用 DeepCode 写代码”的体验,方便团队在日常协作中直接使用 AI 编程能力。 This release…

Read full notes

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 README_ZH.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。 此版本重点提升了“在聊天软件中用 DeepCode 写代码”的体验,方便团队在日常协作中直接使用 AI 编程能力。

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 task status queries, with new real-world Feishu screenshots in the docs. Docs overhaul: Both README.md and README_ZH.md have been updated with a cleaner Quick Start, and a dedicated nanobot Integration (Feishu Chatbot) section that walks you through configuration and deployment end-to-end. This version makes it much easier to use DeepCode as a coding assistant directly inside your team’s chat workflow.

Monday, February 9Feb 9, 2026

Release v1.1.0

DeepCode v1.1.0

DeepCode v1.1.0 重磅更新!新增 Docker 容器化支持,一键部署,开箱即用。让代码分析更简单,部署更便捷! DeepCode v1.1.0 Major Update! Now with Docker containerization support - one-click deployment, ready to use out of the box. Making code analysis simpler and deployment easier!

Read full notes

DeepCode v1.1.0 重磅更新!新增 Docker 容器化支持,一键部署,开箱即用。让代码分析更简单,部署更便捷!

DeepCode v1.1.0 Major Update! Now with Docker containerization support - one-click deployment, ready to use out of the box. Making code analysis simpler and deployment easier!

Wednesday, February 4Feb 4, 2026

Release v1.0.9

DeepCode v1.0.9

DeepCode v1.09 - New UI Update The new React-based web interface is now available with these improvements: Interactive workflow - AI can ask follow-up questions during code generation Streamlined interface - Questions appear directly in the chat for better…

Read full notes

DeepCode v1.09 - New UI Update The new React-based web interface is now available with these improvements: Interactive workflow - AI can ask follow-up questions during code generation Streamlined interface - Questions appear directly in the chat for better visibility Cross-platform - Works on Windows, macOS, and Linux with deepcode command Better stability - Improved process handling and automatic port management Run deepcode to try the new interface, or use deepcode --classic for the previous version.

DeepCode v1.09 - 新 UI 更新 基于 React 的新版 Web 界面现已可用,主要改进包括: 交互式工作流 - AI 可以在代码生成过程中提出后续问题 简化的界面 - 问题直接显示在对话中,更易于查看 跨平台支持 - 使用 deepcode 命令在 Windows、macOS 和 Linux 上运行 更好的稳定性 - 改进的进程处理和自动端口管理 运行 deepcode 体验新界面,或使用 deepcode --classic 使用旧版本。

Wednesday, November 19Nov 19, 2025

Release v1.0.8

DeepCode v1.0.8

Support for Google Gemini official API: DeepCode now supports configuration of Google’s official Gemini API, including full support for Gemini‑3‑pro. 支持 Google Gemini 官方 API 已支持配置 Google Gemini 大模型的官方 API,并完成对 Gemini‑3‑pro 的适配与使用。

Read full notes

Support for Google Gemini official API: DeepCode now supports configuration of Google’s official Gemini API, including full support for Gemini‑3‑pro.

支持 Google Gemini 官方 API 已支持配置 Google Gemini 大模型的官方 API,并完成对 Gemini‑3‑pro 的适配与使用。

Tuesday, November 18Nov 18, 2025

Release v1.0.7

DeepCode v1.0.7

New Version: We have updated DeepCode’s overall workflow and fixed several issues and bugs previously reported by users. We have improved the robustness of the system and introduced targeted optimizations for models with relatively weaker coding capabilities.…

Read full notes

New Version:

  1. We have updated DeepCode’s overall workflow and fixed several issues and bugs previously reported by users.

  2. We have improved the robustness of the system and introduced targeted optimizations for models with relatively weaker coding capabilities.

  3. Our currently recommended most stable and high‑quality large language models include: Claude 3.5 and above, GPT‑4o and above, and Gemini‑pro.

  4. We will continue to iterate, further refining the workflow and robustness, and adapting the system for stable operation across multiple model families. Future roadmap:

  5. DeepCode will release related technical reports.

  6. We will launch automated code verification and execution features.

  7. We will keep iterating and advancing the system through continuous technological innovation and adoption.

新版本:

  1. 我们已对 DeepCode 的整体 workflow 进行了更新,修复了此前大家反馈的一些问题和 Bug。
  2. 提升了模型的鲁棒性,并针对部分代码能力相对较弱的模型进行了专项优化。
  3. 当前推荐使用的最稳定且高质量的大语言模型包括:Claude 3.5 及以上版本、GPT‑4o 及以上版本,以及 Gemini‑pro。
  4. 我们将持续迭代,进一步优化 workflow 与鲁棒性,并针对多种模型进行稳定性适配。

未来规划:

  1. DeepCode 将发布相关技术报告;
  2. 上线代码自动化验证与执行功能;
  3. 持续迭代升级,引入和落地更多前沿技术。

Full Changelog: https://github.com/HKUDS/DeepCode/compare/v1.0.6...v1.0.7

Monday, November 10Nov 10, 2025

Thursday, October 2Oct 2, 2025

Release v1.0.5

DeepCode v1.0.5

Got a brilliant idea in mind but don’t know where to start? It’s time to let the Agent become your product manager! DeepCode Major Update! We are introducing a brand-new personalized requirements customization feature. It’s a new interactive feature that turns…

Read full notes

Got a brilliant idea in mind but don’t know where to start? It’s time to let the Agent become your product manager! DeepCode Major Update! We are introducing a brand-new personalized requirements customization feature.

It’s a new interactive feature that turns vague ideas into actionable development plans. Instead of requiring you to provide detailed specifications up front, DeepCode’s Agent will:

  • Ask clarifying questions about your idea.
  • Break down abstract requirements into concrete functional specifications.
  • Continuously refine and optimize the plan based on your additional input.
  • Adapt dynamically until the final plan matches exactly what you need.

From a single sentence to a complete project blueprint—experience the magic of co-creating with AI right now! This update also brings a brand-new UI with a smoother and more intuitive experience. Coming soon, we’ll add powerful features like automated testing and performance dashboards. But this is just the beginning. Our roadmap includes even more exciting features:

Automated Verification and Optimization Agents: automated testing, sandbox verification, and a more comprehensive coding experience.

Benchmark Dashboards: detailed performance metrics on the PaperBench evaluation suite to stay transparent and ahead.

System-Wide Optimizations: stronger reasoning and broader multi-language framework support.

We are building the future of software development—stay tuned! Try it now: https://github.com/HKUDS/DeepCode

Full Changelog: https://github.com/HKUDS/DeepCode/compare/v1.0.4...v1.0.5

Friday, August 8Aug 8, 2025

Friday, July 25Jul 25, 2025

Wednesday, July 23Jul 23, 2025

Release v1.0.2

DeepCode v1.0.2

Hot Fix Fixed the issue where file conversion would get stuck, and added compatibility for Windows systems. Full Changelog: https://github.com/HKUDS/DeepCode/compare/v1.0.1...v1.0.2

Read full notes

Hot Fix

  • Fixed the issue where file conversion would get stuck, and added compatibility for Windows systems.

Full Changelog: https://github.com/HKUDS/DeepCode/compare/v1.0.1...v1.0.2

Monday, July 21Jul 21, 2025

Release v1.0.0

DeepCode v1.0.0

New release!

Read full notes

New release!