TRACEABLE OPEN-SOURCE DEMAND SIGNALS

Opportunity Radar

We scan public GitHub Issues for recurring requests, workflow friction and missing capabilities—then rank the strongest signals without hiding the original evidence.

62 signals · Last data refresh Nov 20, 2026, 11:30 PM UTC

ISSUE SCAN COVERAGE35 / 36 current repositories · 5 new

“New” means first detected by the Radar within 48 hours. Live opportunities come only from projects in the current curated feed; archived projects remain searchable as historical research but cannot leave stale demand signals here.

Demand confidence
Professional field
Problem theme
Evidence signal, not proof of market demand.

A popular Issue can reveal real friction, but it does not prove willingness to pay. Use these leads for interviews, validation and product discovery.

FROM SIGNAL TO ACTION

A 3-step validation sprint

Use the evidence as a starting point, then verify the problem before building.

  1. 1. Read the threadIdentify who has the problem and the workaround they use today.
  2. 2. Contact five usersAsk about frequency, cost and what they already tried.
  3. 3. Test one narrow fixOffer a manual or lightweight solution before writing a full product.
31 Product Capability signals
#1
Provider interoperability · CodingREPEATED ACROSS 11 PROJECTS

Add gemini-3.1-pro-preview

Observed in google-gemini/gemini-cli · TypeScript · Apache-2.0

What the reporter described: What happened? gemini-3.1-pro-preview isn't in the models list What did you expect to happen? gemini-3.1-pro-preview is in the models list Client information <details <summary Client Information</summary Run to enter the interactive CLI, then run the command. </details Login information Google account Anything else we…

Related friction appears in 11 independent repositories. This is stronger than one backlog item, but still requires direct user validation.

127 comments110 positive reactions274 days openEvidence score 91/100Project Radar 100
priority/p1area/enterprisekind/customer-issue🔒 maintainer only
#2
Tool execution & lifecycle · ResearchREPEATED ACROSS 3 PROJECTS

Support dynamic tool addition/removal after agent creation and in middleware

Observed in langchain-ai/langchain · Python · MIT

What the reporter described: Checked other resources [x] This is a feature request, not a bug report or usage question. [x] I added a clear and descriptive title that summarizes the feature request. [x] I used the GitHub search to find a similar feature request and didn't find it. [x] I checked the LangChain documentation and API reference to see…

Related friction appears in 3 independent repositories. This is stronger than one backlog item, but still requires direct user validation.

19 comments16 positive reactions382 days openEvidence score 89/100Project Radar 97
langchainfeature requestcandidateexternal
#3
Product Capability workflows · ResearchREPEATED ACROSS 13 PROJECTS

[FEAT] Add deterministic pre-action authorization at the tool-call hook level

Observed in VoltAgent/voltagent · TypeScript · MIT

What the reporter described: Is your feature request related to a problem? Please describe. VoltAgent's guardrail system validates content but doesn't deterministically authorize tool execution before it happens. With MCP servers proliferating, agents face silent injection risks where a poisoned prompt triggers unintended tool calls. The Open…

Related friction appears in 13 independent repositories. This is stronger than one backlog item, but still requires direct user validation.

23 comments10 positive reactions246 days openEvidence score 81/100Project Radar 89
enhancement
#4
Tool execution & lifecycle · CodingREPEATED ACROSS 3 PROJECTS

Still can't figure out how to get v3 to actually perform work.

Observed in ruvnet/ruflo · TypeScript · MIT

What the reporter described: First off, let me commend the contributors for an amazing, product, and from what I see in the v3 docs, this looks like a pretty fantastic rewrite. But to be honest, I've been very confused when trying to use v3. Should it have command compatibility with 2.7.x to some degree? I'm able to spawn a hive mind or start a…

Related friction appears in 3 independent repositories. This is stronger than one backlog item, but still requires direct user validation.

19 comments2 positive reactions307 days openEvidence score 79/100Project Radar 100
#5
Product Capability workflows · CodingREPEATED ACROSS 13 PROJECTS

analyst agent is never 'found'

Observed in ruvnet/ruflo · TypeScript · MIT

What the reporter described: I've noticed this a number of times now, using r88 analyst(Analyze VSDX format) ⎿ Initializing… ⎿ Error: Agent type 'analyst' not found. Available agents: general-purpose, api-docs, cicd-engineer, tdd-london-swarm, production-validator, backend-dev, pseudocode, specification, refinement, architecture, ml-developer,…

Related friction appears in 13 independent repositories. This is stronger than one backlog item, but still requires direct user validation.

10 comments6 positive reactions471 days openEvidence score 79/100Project Radar 100
#6
Human approval & safety · CodingREPEATED ACROSS 2 PROJECTS

Seats blocked on a permission prompt (needs_input) don't raise rig attention or any watchdog alert

Observed in mvschwarz/openrig · TypeScript · Apache-2.0

What the reporter described: Summary A seat blocked on a runtime permission prompt is detected per-seat ( / ) but that signal never reaches anyone: the rig-level attention count ignores it and no watchdog policy can fire on it. In practice a Claude Code seat sat on a tool-approval prompt for 1.5 h in a 6-seat rig with an orchestrator and an…

Related friction appears in 2 independent repositories. This is stronger than one backlog item, but still requires direct user validation.

16 comments1 positive reactions54 days openEvidence score 71/100Project Radar 96
bugarea: status-tuiconfirmed
#7
Tool execution & lifecycle · CodingREPEATED ACROSS 3 PROJECTS

Feature Request: Support agent.pause() within tool calls

Observed in browser-use/browser-use · Python · MIT

What the reporter described: What is the problem that your feature request solves? Feature request: human-in-the-loop pause that suspends Problem There is no first-class way for a tool to pause the agent, wait for external input (a human clarification, an approval, a signal from another process), and then resume — without falling foul of . The…

Related friction appears in 3 independent repositories. This is stronger than one backlog item, but still requires direct user validation.

20 comments0 positive reactions198 days openEvidence score 70/100Project Radar 99
NEW SIGNALenhancement
#8
Product Capability workflows · CodingREPEATED ACROSS 13 PROJECTS

[FEAT] Multiple Claude Accounts

Observed in 777genius/agent-teams-ai · TypeScript · AGPL-3.0

What the reporter described: Summary We have multiple claude teams as a solution to prevent huge cost. A developer can have multiple premium seats, even in the same team with another e-mailadres. Problem It seems the claude provider only supports one user session. Area Provider runtime: Claude Describe the solution you'd like Allow multiple login…

Related friction appears in 13 independent repositories. This is stronger than one backlog item, but still requires direct user validation.

6 comments3 positive reactions66 days openEvidence score 68/100Project Radar 90
enhancement
#9
Provider interoperability · Agent InfrastructureREPEATED ACROSS 11 PROJECTS

feat: Add support for OpenAI-compatible LLM endpoints (Groq, Ollama, Azure OpenAI, etc.)

Observed in google/adk-java · Java · Apache-2.0

What the reporter described: 🔴 Required Information Is your feature request related to a specific problem? Yes. Currently, ADK-Java only supports Google's Gemini and Claude models out of the box. Developers cannot easily use other LLM providers that implement the OpenAI Chat Completions API format, such as: Groq (fast inference with open models)…

Related friction appears in 11 independent repositories. This is stronger than one backlog item, but still requires direct user validation.

11 comments3 positive reactions188 days openEvidence score 68/100Project Radar 89
needs review
#10
Product Capability workflows · CodingREPEATED ACROSS 13 PROJECTS

Stall checks miss unsubmitted wakes and flag waiting or working seats

Observed in mvschwarz/openrig · TypeScript · Apache-2.0

What the reporter described: OpenRig version 0.6.3, commit . OS, Node and tmux versions Debian 13 under WSL2, Node 24.21.0, tmux 3.7c. Node and tmux versions were read back while preparing this draft on 2026-10-01. Harnesses involved Claude Code and Codex. What you ran and what happened Our local intake records two missed stalls on 2026-10-01. A…

Related friction appears in 13 independent repositories. This is stronger than one backlog item, but still requires direct user validation.

22 comments0 positive reactions50 days openEvidence score 67/100Project Radar 96
bugarea: deliveryconfirmed
#11
Product Capability workflows · ProductivityREPEATED ACROSS 13 PROJECTS

[Feature] Images are never passed to the main model — every image goes through a text bottleneck in the toolvision

Observed in zhayujie/CowAgent · Python · MIT

What the reporter described: Self check [x] I searched existing issues (incl. closed) — no duplicate. What's the problem? Summary When a user sends an image, CowAgent never delivers the image itself to the main model. Instead the image is reduced to a file path in the user message, and the main model must decide on its own to call the tool, which…

Related friction appears in 13 independent repositories. This is stronger than one backlog item, but still requires direct user validation.

5 comments1 positive reactions44 days openEvidence score 66/100Project Radar 99
#12
Product Capability workflows · ResearchREPEATED ACROSS 13 PROJECTS

[Bug]: When extracting data with scroll_full_page, only the final elements get parsed

Observed in unclecode/crawl4ai · Python · Apache-2.0

What the reporter described: crawl4ai version 0.4.248 Expected Behavior I'm crawiling Twitter, specifically the "following" section of a profile. I have a css selector for the relevant data (user's names and bios) and set up a JsonCssExtractionStrategy. If I don't use scroll full page, I understandably only expect to get the first N user…

Related friction appears in 13 independent repositories. This is stronger than one backlog item, but still requires direct user validation.

22 comments0 positive reactions638 days openEvidence score 63/100Project Radar 100
🐞 Bug⚙️ In-progress
#13
Provider interoperability · SecurityREPEATED ACROSS 11 PROJECTS

feat: 本地运行模式、Gemini/Codex 适配器、i18n 国际化、定时启动及项目管理增强

Observed in oritera/Cairn · Python · AGPL-3.0

What the reporter described: 概述 以下是在 Cairn fork 版本中开发的一系列功能增强,分享给上游以供参考,欢迎讨论是否有合并的价值。 --- 新增功能 1. 本地运行模式(无需 Docker) 新增 ,作为 的无 Docker 替代方案。Worker 直接通过 subprocess 在宿主机上运行,通过 中的 启用。 使用原生 Python 超时处理(无需 GNU timeout) 与 ContainerManager 保持相同的文件写入契约,任务代码兼容 适合无 Docker 的开发/测试环境 2. 简化 Worker 适配器 重构了 Claude Code 和 Codex 适配器,直接使用本地已认证的 CLI,无需在配置中填写 API Key 或…

Related friction appears in 11 independent repositories. This is stronger than one backlog item, but still requires direct user validation.

1 comments7 positive reactions189 days openEvidence score 62/100Project Radar 85
#14
Human approval & safety · ProductivityREPEATED ACROSS 2 PROJECTS

[Bug] CowAgent have risk leaking user's privacy and executing destruction commands on user's computer

Observed in zhayujie/CowAgent · Python · MIT

What the reporter described: Self check [x] I'm on the latest version and searched existing issues (incl. closed) — no duplicate. Environment Version: Newest Version Platform: macOS 26.4 Form: Desktop App Model: Deepseek / Claude Opus ... This applies for any models. What happened? Invite the CowAgent bot to Feishu(Lark). use"@" to call the bot,…

Related friction appears in 2 independent repositories. This is stronger than one backlog item, but still requires direct user validation.

7 comments0 positive reactions113 days openEvidence score 61/100Project Radar 99
#15
Product Capability workflows · SecurityREPEATED ACROSS 13 PROJECTS

这是我在GitHub上见过最好的AI项目,没有之一。这个实在是太牛逼了,兄弟们要慧眼识珠啊

Observed in oritera/Cairn · Python · AGPL-3.0

What the reporter described: 嗯,如题,内容我就不写了,我给他魔改了

Related friction appears in 13 independent repositories. This is stronger than one backlog item, but still requires direct user validation.

1 comments3 positive reactions75 days openEvidence score 59/100Project Radar 85
#16
Product Capability workflows · CodingREPEATED ACROSS 13 PROJECTS

[FEAT] oMo native support

Observed in 777genius/agent-teams-ai · TypeScript · AGPL-3.0

What the reporter described: Summary Support the harness oMo native Problem oMo native is a new harness evolve from the plugin of opencode, agent-teams-ai currently have no support of it. Area Which part of the app would this affect? Provider runtime (Claude, Codex, OpenCode) Describe the solution you'd like Support oMo native Describe…

Related friction appears in 13 independent repositories. This is stronger than one backlog item, but still requires direct user validation.

4 comments1 positive reactions52 days openEvidence score 59/100Project Radar 90
#17
Product Capability workflows · SecurityREPEATED ACROSS 13 PROJECTS

[Bug]: AI Agents Settings cannot be saved

Observed in vxcontrol/pentagi · Go · MIT

What the reporter described: Affected Component Other (please specify in the description) Describe the bug What happend: I deployed PENTAGI with the ./installer and run a Task. Now i want to edit the config with the /installer. When i open "AI Agents Settings" i cannot save my changes. In the other categories like "Search Engines Configration" i…

Related friction appears in 13 independent repositories. This is stronger than one backlog item, but still requires direct user validation.

5 comments0 positive reactions37 days openEvidence score 59/100Project Radar 100
bug
#18
Product Capability workflows · FinanceREPEATED ACROSS 13 PROJECTS

Proposal: benchmark-relative Information Ratio for fixed-income fund analytics

Observed in OpenByteInc/QuantDinger · Python · Apache-2.0

What the reporter described: Motivation Fixed-income fund performance should be evaluated relative to an appropriate benchmark rather than through absolute return alone. I propose adding a benchmark-relative Information Ratio metric, initially supporting CDI for Brazilian cash-like and low-duration fixed-income funds while keeping the benchmark…

Related friction appears in 13 independent repositories. This is stronger than one backlog item, but still requires direct user validation.

6 comments0 positive reactions124 days openEvidence score 59/100Project Radar 97
#19
Provider interoperability · DesignREPEATED ACROSS 11 PROJECTS

Hermes support

Observed in OpenMontageInc/OpenMontage · Python · AGPL-3.0

What the reporter described: Hey Folks is there any support for hermes agent

Related friction appears in 11 independent repositories. This is stronger than one backlog item, but still requires direct user validation.

5 comments0 positive reactions149 days openEvidence score 58/100Project Radar 98
NEW SIGNAL
#20
Product Capability workflows · General AIREPEATED ACROSS 13 PROJECTS

[Feature] Long-form courses: 25-240 minute lessons with a critique/repair loop

Observed in THU-MAIC/OpenMAIC · TypeScript · MIT

What the reporter described: Problem The generation pipeline assumes a short lesson. A request that names an hour is planned by the same rules as a request that names fifteen minutes, and the result is one of two failures: A sprint. The scene-count guidance is "1-2 scenes per minute", so an hour becomes 60-120 pages, each with a paragraph of…

Related friction appears in 13 independent repositories. This is stronger than one backlog item, but still requires direct user validation.

8 comments0 positive reactions19 days openEvidence score 57/100Project Radar 89
NEW SIGNAL
#21
Product Capability workflows · Agent InfrastructureREPEATED ACROSS 13 PROJECTS

Terminal.run_command() hangs indefinitely on Linux/WSL2 — end-of-command marker never yielded from splitlines/tuple-unpack

Observed in FoundationAgents/MetaGPT · Python · MIT

What the reporter described: Summary hangs indefinitely on Linux/WSL2 whenever the persistent shell's stdout ends with the end-of-command marker as the final line (i.e., always, under normal conditions). The read loop in uses after reading each byte, but when the buffer contains exactly one -terminated line, the tuple-unpacking idiom moves that…

Related friction appears in 13 independent repositories. This is stronger than one backlog item, but still requires direct user validation.

6 comments0 positive reactions124 days openEvidence score 56/100Project Radar 76
inactive
#22
Setup & configuration · FinanceREPEATED ACROSS 3 PROJECTS

希望可以实现Docker部署

Observed in ValueCell-ai/valuecell · Python · Apache-2.0

What the reporter described: 希望可以出一套Docker部署的方法

Related friction appears in 3 independent repositories. This is stronger than one backlog item, but still requires direct user validation.

3 comments2 positive reactions356 days openEvidence score 55/100Project Radar 75
enhancementgood first issue
#23
Product Capability workflows · FinanceREPEATED ACROSS 13 PROJECTS

Use Laya as an alternative to Jev

Observed in OpenByteInc/QuantDinger · Python · Apache-2.0

What the reporter described: motivation Use Laya as an alternative to Jev Hi, I’m interested in using Laya instead of Jev for the decision-making/evaluation part of the system. Laya is an open-source alternative that can be self-hosted locally, which would be useful for running without depending on the Jev API. Repository: [link] Questions How is…

Related friction appears in 13 independent repositories. This is stronger than one backlog item, but still requires direct user validation.

4 comments0 positive reactions54 days openEvidence score 55/100Project Radar 97
enhancement
#24
Context & memory boundaries · MarketingREPEATED ACROSS 4 PROJECTS

Avoid predictable fallback credentials (session secret, Slack token)

Observed in langchain-ai/social-media-agent · TypeScript · MIT

What the reporter described: Summary Two code paths silently fall back to hardcoded placeholder credentials when the corresponding environment variable is unset. These are not leaked production secrets, but they are predictable default values that should fail fast instead of being used for authentication/session signing. Findings 1. —…

Related friction appears in 4 independent repositories. This is stronger than one backlog item, but still requires direct user validation.

2 comments0 positive reactions85 days openEvidence score 53/100Project Radar 87
#25
Product Capability workflows · DesignREPEATED ACROSS 13 PROJECTS

[Feature] Figma-style canvas comments for collaboration with agents

Observed in ZSeven-W/openpencil · Rust · MIT

What the reporter described: Please add Figma-style canvas comments : users leave feedback on specific elements in the GUI; agents working in a terminal discover comments through MCP, update the canvas, and reply. Three statuses Status Meaning Who can change it --- --- --- Pending Feedback waiting to be addressed User / AI Addressed Changes or a…

Related friction appears in 13 independent repositories. This is stronger than one backlog item, but still requires direct user validation.

2 comments0 positive reactions23 days openEvidence score 51/100Project Radar 93
#26
Provider interoperability · DesignREPEATED ACROSS 11 PROJECTS

希望可以支持gemini模型,还有stitch的导入

Observed in ZSeven-W/openpencil · Rust · MIT

What the reporter described: Problem codex和claude的审美不好,gemini模型的审美要好些 Proposed Solution 支持gemini模型,希望还可以支持google的stitch导入 Alternatives Considered No response Area None Additional Context No response

Related friction appears in 11 independent repositories. This is stronger than one backlog item, but still requires direct user validation.

4 comments0 positive reactions245 days openEvidence score 51/100Project Radar 93
enhancement
#27
Product Capability workflows · MarketingREPEATED ACROSS 13 PROJECTS

Media constraints: correct the platform limits, then measure video server-side

Observed in trypostit/trypost · PHP · AGPL-3.0

What the reporter described: Design and implementation plan for the media-constraint work, ready to execute. Supersedes the approach in #287 and covers all three goals of #200. Full design doc and the Phase 1 task-by-task plan are attached as comments below, so this issue is self-contained. Why #287 can't be merged as-is PR #287 extended from…

Related friction appears in 13 independent repositories. This is stronger than one backlog item, but still requires direct user validation.

2 comments0 positive reactions85 days openEvidence score 50/100Project Radar 86
enhancement
#28
Strategy & provenance · FinanceREPEATED ACROSS 2 PROJECTS

After the trading strategy agent is set up, it automatically stops and cannot be started.

Observed in ValueCell-ai/valuecell · Python · Apache-2.0

What the reporter described: Hi, I have now configured the API key as required, and I have also deposited funds and completed the setup for both OpenRouter and OKX. However, after I finish configuring the trading strategy, it automatically stops, as shown in the screenshot. I’m not sure what the problem is. How can I set up automatic trading, and…

Related friction appears in 2 independent repositories. This is stronger than one backlog item, but still requires direct user validation.

6 comments0 positive reactions357 days openEvidence score 49/100Project Radar 75
#29
Strategy & provenance · FinanceREPEATED ACROSS 2 PROJECTS

Feedback request: structured strategy representation and provenance layer for financial agents

Observed in AI4Finance-Foundation/FinRobot · Python · Apache-2.0

What the reporter described: Background I maintain an early-stage open-source project called QST. QST tries to represent quantitative trading strategies in a structured format that is easier to transmit, validate, store, compare, and process by agents or automated research systems. It is not a reinforcement learning environment, backtesting…

Related friction appears in 2 independent repositories. This is stronger than one backlog item, but still requires direct user validation.

2 comments0 positive reactions188 days openEvidence score 47/100Project Radar 91
#30
Product Capability workflows · MarketingREPEATED ACROSS 13 PROJECTS

[Enhancement] Unpublish & Delete posts

Observed in trypostit/trypost · PHP · AGPL-3.0

What the reporter described: Problem Currently if someone publishes something by accident they need to: Log into the designated platform (e.g. instagram) and delete the post manually Copy the "published" post to edit it and publish again This leaves a ghost published post in the trypost database. Proposed solution Both functions should require…

Related friction appears in 13 independent repositories. This is stronger than one backlog item, but still requires direct user validation.

2 comments0 positive reactions108 days openEvidence score 46/100Project Radar 86
#31
Provider interoperability · MarketingREPEATED ACROSS 11 PROJECTS

Support few more llms

Observed in langchain-ai/social-media-agent · TypeScript · MIT

What the reporter described: Only anthropic is supported as of now Is there any plans on supporting other llms

Related friction appears in 11 independent repositories. This is stronger than one backlog item, but still requires direct user validation.

2 comments0 positive reactions674 days openEvidence score 43/100Project Radar 87

How opportunities are ranked

The evidence score combines capped, diminishing-return discussion, positive reactions, unresolved duration and the underlying project’s Radar Score. This prevents one repeatedly commented thread from overwhelming independent signals. Maintenance-only tickets, dependency dashboards, CI failures and release checklists are filtered out. Rankings are independent and never paid placements.