Preparing the page…

Taking longer than expected? Reload

CATEGORY INTELLIGENCE / WORLDWIDE

Coding agents

Agents that navigate, write and ship code.

Red ocean · Measured classification

Coding agents: Cooling recently, still above last year

Search attention for “coding agent” is falling. 46 reviewed open-source projects serve this task. Recent search attention is cooling while staying above last year's level. Use interviews and product usage to assess customer demand.

Report dated 2026-10-22 · Method 2.0.0 · moderate evidence confidence

Measured search term: coding agent · Last 8 complete weeks vs previous 8

4479 active projects match the published GitHub search scope.
The keyword “coding agent” has 104 complete weeks; 13% are reported as zero.

Open-source competition: ≥97 / 100 · Established alternatives
Open-source alternatives: 46
Direction basis: Recent search windows
Matching active GitHub projects: 4,479
Search-interest growth: -45% · Last 8 complete weeks vs previous 8
Search term and region: coding agent · Worldwide
Complete weekly observations: 104

Why this classification

Recent search attention is cooling while staying above last year's level. Both horizons provide context.
Median weekly search interest fell 45% across two consecutive eight-week windows.
4,479 active repositories match this search scope. Review their users and workflows to identify direct alternatives.
Four-week search change: -49%; thirteen-week change: -60%. These windows check the direction of the eight-week comparison.
Project roles: 46 direct alternatives, 0 adjacent projects, 2 resources, 52 awaiting review.
Competition pressure: 98–100/100; breadth 48, established alternatives 30, leading project strength 20.

Source evidence

GitHub repository search · topic:coding-agent fork:false archived:false stars:>=1 pushed:>=2025-10-22

Collected 2026-10-22T07:34:24.501Z

Google Trends search interest · Collected 2026-10-22T07:34:24.501Z

Leading repositories

Repository	Stars	Description
openinterpreter/openinterpreter	68,632	A coding agent for open models like Kimi K3 and GLM 5.3
hesreallyhim/awesome-claude-code	56,219	A hand-picked collection of the finest of resources for the most awesome of agents, Claude Code, the undisputed champion of coding companions, from the unstoppable team at Anthropic PBC (no affiliation). A delectable showcase of top tier skills, ambidextrous agents, scintillating status lines, top notch developer tooling, and also we have plugins
bojieli/ai-agent-book	55,387	《深入理解 AI Agent：设计原理与工程实践》（李博杰著）开源主仓库：全书正文、编译版 PDF 与按章配套代码
codewhale-hq/Codewhale	41,105	Open-source Rust agent engine and terminal client for Codewhale, with provider choice, tools, approvals and receipts.
esengine/DeepSeek-Reasonix	35,907	A reliable coding agent for complex software engineering tasks.
QwenLM/qwen-code	28,640	An open-source AI coding agent that lives in your terminal.
OthmanAdi/planning-with-files	27,576	Persistent file-based planning for AI coding agents and long-running tasks. Crash-proof markdown plans, session recovery after /clear and compaction, per-turn re-injection against context rot, deterministic completion gate. Manus-style. Install from npm, the Claude Code plugin marketplace, or npx skills. Codex, Cursor, OpenCode, 60+ agents.
1jehuang/jcode	21,114	High performance coding agent harness written in Rust, built for heavy multi-agent dev workflows
NanmiCoder/cc-haha	15,110	本地优先的跨平台 Claude Code / AI Agent 桌面工作台：多 Agent 协作、Git Worktree、代码 Diff、技能市场、多模型、Computer Use、桌面宠物；支持微信、飞书、钉钉及 H5 等远程访问。 \| Local-first Claude Code / AI Agent desktop workspace: multi-agent teams, Git worktrees, diffs, skills marketplace, multi-model, Computer Use, task-aware desktop pets; remote via WeChat, Feishu, DingTalk, Telegram, WhatsApp & H5.
YaoApp/yao	8,177	✨ All your agents and workspaces in one place, on every device you own. Track tasks on a board, accessible from desktop, mobile, browser, or API. Self-hosted.

Limits of this result

Google Trends measures relative search attention. Assess customers, revenue and willingness to pay through direct research.
Supply covers active repositories matching the displayed GitHub queries. Broader competition research can include other repositories and commercial products.
Repository density and search attention provide complementary research signals. Assess competition and demand through user and product evidence.
Competition pressure is an operational index of observed open-source alternatives. Stars and forks indicate developer attention and reuse; user adoption and commercial products deserve separate research.
The displayed projects form a stars-ranked sample. Competition pressure is a lower bound; wider coverage can strengthen the assessment.
Some project roles await closer review. The pressure range includes their possible contribution.

Search interest measures attention. Customer demand needs user research; classification thresholds are published heuristics subject to empirical calibration.

Community requests

ollama qwen coder model support

Discussion open

What would you like to be added? Please add support for ollama self hosted models , Right now local models either just work as chat or dont work at all . I tried changing ollama context setting but it didnt help. Why is this needed? The same models in clo

QwenLM/qwen-code · Posted: 2025-08-02 · Updated: 2026-01-05 · Collected: 2026-10-22

Add a setting to make top-level subagents run in the foreground by default

Discussion open

What would you like to be added? A user/project-level setting that flips the default execution mode of top-level regular subagents from background to foreground, for example: json { "agents": { "defaultBackground": false } } Current precedence is: the exp

QwenLM/qwen-code · Posted: 2026-10-22 · Updated: 2026-10-22 · Collected: 2026-10-22

[Feature]: 提个建议，先做一版稳定版吧

Discussion open

Version line v2 — Go rewrite (1.x), main-v2 (active development) What problem does this solve? 建议不要推送非稳定版的更新，做一下稳定版与前瞻版的隔离。我用了大概半个月，也帮忙解决过bug。我的需求很简单，就是想要一个可用的，提高我生产力的工具。现在几乎每更新一次都有新的功能添加进来，然后诞生新的bug。我需要的是一个稳定的产品，如果有时间或者精力我也会参与其中（前瞻版本），而不是每天都要手动clon

esengine/DeepSeek-Reasonix · Posted: 2026-08-12 · Updated: 2026-10-12 · Collected: 2026-10-22

Better ACP & IDE integration

Discussion open

This task tracks all ACP integration issues.

QwenLM/qwen-code · Posted: 2025-11-07 · Updated: 2026-03-19 · Collected: 2026-10-22

Managed Agent: support closing, archiving and deleting public Shell Sessions

Discussion open

What would you like to be added? A way to close, archive, unarchive and delete Managed Agent Sessions that were created with public Shell access. These four lifecycle operations are currently refused for public Shell Sessions, including on protocol-0, while

QwenLM/qwen-code · Posted: 2026-10-21 · Updated: 2026-10-22 · Collected: 2026-10-22

[Feature Request] Hope to add support for the qwen3-coder-next model as soon as possible.

Discussion open

What would you like to be added? @dewitt @motdotla @trapezoid @ptone @teeler Hope to add support for the latest qwen3-coder-next coding model as soon as possible. Thank you! 👍 Why is this needed? The latest qwen3-coder-next delivers enhanced performanc

QwenLM/qwen-code · Posted: 2026-02-07 · Updated: 2026-02-07 · Collected: 2026-10-22

feat: harness SWE — feature-type benchmark tasks that exercise and demo qwen code's own features

Discussion open

A "harness SWE" benchmark suite: original, feature-type software-engineering tasks (realistic small repos, feature-implementation instructions, behavior verifiers) written specifically to exercise qwen code's own feature surface — todo tracking, plan mode, ski

QwenLM/qwen-code · Posted: 2026-10-13 · Updated: 2026-10-13 · Collected: 2026-10-22

[Feature]: Add to acp-registry

Discussion open

Version line v2 — Go rewrite (1.x), main-v2 (active development) What problem does this solve? https://github.com/agentclientprotocol/registry https://zed.dev/blog/acp-registry Proposed solution No response

esengine/DeepSeek-Reasonix · Posted: 2026-06-08 · Updated: 2026-09-27 · Collected: 2026-10-22

Auto-mode permission classifier resilience: fail-open on unavailability (regression of #7331), deterministic allow-rule short-circuit, configurable timeout/fallback

Discussion open

Context CLI 2.1.234, non-default model provider (OpenAI-compatible endpoint), two-stage auto-mode permission classifier (fast tier for stage-1 per-command checks, stronger tier for stage-2). During provider-side instability waves (observed 2026-08-17 and 202

QwenLM/qwen-code · Posted: 2026-08-21 · Updated: 2026-09-24 · Collected: 2026-10-22

`qwen serve`: built-in shell guard ignores the session approval mode, denies read-only Git and non-Git commands outside the session directory, and cannot be configured, audited, or surfaced to the operator

Discussion open

What happened? Scope: the qwen serve daemon and its Web Shell. Nothing in this report concerns the interactive CLI, its approval prompts, or its own CLI-only mode controls. "Full access" below is the label the Web Shell shows the operator for the approval mo

QwenLM/qwen-code · Posted: 2026-09-03 · Updated: 2026-09-03 · Collected: 2026-10-22

feat: Add dynamic multi-model support for OpenAI-compatible APIs

Discussion open

What would you like to be added? Add support for dynamically fetching and switching between multiple models from OpenAI-compatible API endpoints. Instead of being limited to a single hardcoded model, users should be able to: 1. Configure an OpenAI-compatibl

QwenLM/qwen-code · Posted: 2025-12-10 · Updated: 2026-06-12 · Collected: 2026-10-22

Native Amazon Bedrock Support

Discussion open

What would you like to be added? Amazon Bedrock started to provide Qwen3-Coder models from 2025-09-18. https://aws.amazon.com/jp/blogs/aws/qwen-models-are-now-available-in-amazon-bedrock/ It's better that qwen code can use bedrock as an auth option. Why

QwenLM/qwen-code · Posted: 2025-10-04 · Updated: 2025-11-14 · Collected: 2026-10-22

Use and share the evidence

Permanent report · Markdown · JSON · PNG card

Use the open-source CLI and MCP server on GitHub