All activity
Zac Zuoleft a comment
Hi everyone! Cline CLI 2.0 is here. It brings the full agentic loop to the terminal. The big updates are parallel agents (spinning up multiple instances) and a headless mode that lets you pipe content directly into CI/CD workflows. It also supports Agent Client Protocol, so you can connect it to editors like Neovim or @Zed. And @Kimi AI - Now with K2.5 is free to use for a limited time. My...

Cline CLI 2.0Parallel agents & headless CI/CD in your terminal
Trusted by 5M+ developers, the Cline CLI brings autonomous coding directly to your command line. Fully open source, redesigned from the ground up. Features parallel agents, headless mode for CI/CD, and ACP support for any editor (Zed, Neovim).

Cline CLI 2.0Parallel agents & headless CI/CD in your terminal
Zac Zuoleft a comment
Hi everyone! To put it simply: This is the Pony Alpha on @OpenRouter. GLM-5 is a monster. It scales to 744B params, with 40B active, and integrates @DeepSeek’s Sparse Attention (DSA) to keep costs down while maintaining long context. But the real story is agentic capability. On Vending Bench 2, simulating a business over a year, it ranks #1 among open-source models with a balance of $4,432....

GLM-5Open-weights model for long-horizon agentic engineering
Stop searching—let the world come to you.
TrendWidget brings live search trends to your Home Screen with a Real-time AI Search engine.
While most AI search rely on stale data, our proprietary real-time engine feeds LLMs with live, source-level data for 100% fresh insights.
- One-Tap Insight: Tap a trend to see why it's viral via AI summaries.
- Zero Hallucination: Real-time indexing for accurate breaking news.
- Global Pulse: US, Japan, and Korea available.

TrendWidgetGoogle&Yahoo Trends on Home screen & AI search engine
When sales teams drown in data, Gro turns it into action. Gro is a unified AI sales engine that brings prospecting, targeting, outreach, and intent tracking into one clean workflow. Powered by a live 1B+ database, AI-driven propensity scoring, multi-channel automation, and intent signals, Gro helps teams focus only on accounts that actually matter. No exports. No fragmented tools. Just precise outbound, end to end.
GroThe best way to prospect and sell with AI
PixelRipple is a full-lifecycle AI ads agent — drop any product link, and it handles the rest: research, creation, and testing at scale. Trained on billions of real converting ads, it replicates proven hooks and structures instead of guessing with templates.
Unlike AI generators focused on "pretty" creatives, PixelRipple is built for performance — find winners faster and actually drive sales. Visuals, videos, and UGC in minutes, not weeks. Built for e-commerce. Start free.

PixelRippleFull-Lifecycle AI Ads Agent that Creates Winning Creatives
Zac Zuoleft a comment
Love the simple, handy tool from @UTCP team! Capturing feedback exactly when it matters (at specific timestamps) is such a smart way to get higher-quality insights. Perfect for product demos and user research.

Video FormsEmbed questionnaires in videos to create interactive forms
Ask questions inside your videos, not around them
VForms lets you embed questions directly into the video itself: right where the feedback actually matters
💬Add questions at specific moments in a video so viewers can give contextual feedback
⏭ Let viewers skip ahead based on their answers
🧠 Collect more accurate, higher-quality insights without leaving the video
Perfect for product demos, UX research, onboarding, and anyone tired of juggling videos + forms

Video FormsEmbed questionnaires in videos to create interactive forms
Zac Zuoleft a comment
Hi everyone! Been following @Quash evolve for the past 6 months, and I really admire how the team prioritized PMF over a hasty launch. Their approach to "maintenance-free" QA is impressive: moving away from brittle scripts to an AI agent that understands context and adapts to UI changes on real devices. This is a massive time-saver for mobile teams. Super happy to see them finally live on PH...
QuashA mobile QA agent that runs tests without scripts
Quash is an intent-driven mobile testing tool that lets you write and run tests in plain language instead of scripts. You can run tests on real devices, cloud devices or local emulators. Quash adapts when the UI changes using built-in self healing, understands app behavior across builds, supports backend validations, reusable test data, test suites and running tests in parallel. Every run generates detailed execution reports with step level intent, actions and screenshots.
QuashA mobile QA agent that runs tests without scripts
Zac Zuoleft a comment
Hi everyone! GPT-5.3-Codex is here. The benchmark jumps are impressive (especially OSWorld going from ~38% to 64%), but I found this specific detail in the announcement most interesting: "GPT‑5.3‑Codex is our first model that was instrumental in creating itself." The team used early versions of the model to debug the training run, manage deployment, and diagnose test results. It basically...
GPT-5.3-CodexExpanding Codex to the full spectrum of computer work
Zac Zuoleft a comment
Hi everyone! I think we are past the phase of simply asking "which model is the best?". Once models cross a certain capability threshold, comparing them to pick a winner loses meaning. Instead, we might wanna treat them as distinct individuals with different tastes and perspectives. That is why Model Council is so interesting. It aggregates these different perspectives. Perplexity does an...
Model Council in PerplexityConsult a council of multiple frontier models at once
Advances the frontier of coding and computer work. SOTA on SWE-Bench Pro (57%) and OSWorld (64%). Features mid-task steerability (interact while it works), 25% faster speeds, and "High" capabilities in cybersecurity.
GPT-5.3-CodexExpanding Codex to the full spectrum of computer work
Model Council runs your query across three top models (like GPT-5.2 & Claude Opus) simultaneously. A synthesizer merges the results, highlighting consensus and conflicts for a higher-confidence answer.
Model Council in PerplexityConsult a council of multiple frontier models at once
Zac Zuoleft a comment
Hi everyone! Agent HQ lets you use Claude and Codex directly inside GitHub and VS Code, alongside Copilot. You can also add custom agents. Being able to swap between agents depending on the task (or just comparing their outputs) is nice. Assign them to issues or PRs and let them work asynchronously. It is interesting to see how they handle the same context differently👾
GitHub Agent HQRun Claude, Codex & Copilot directly in GitHub & VS Code
Zac Zuoleft a comment
Hi everyone! True "listen-while-speaking" capability is still hard to get right, especially for open models. Interruptions often don't feel quite seamless. MiniCPM-o 4.5 fixes this with full-duplex. It listens while it speaks, so you can interrupt it naturally. It feels much more like a real conversation. The crazy part is it does this locally (it is only 9B!). It supports llama.cpp and Ollama...

MiniCPM-o 4.5Real-time, full-duplex multimodal AI on your device
A 9B omni-modal model that sees, listens, and speaks simultaneously. Features full-duplex streaming (no turn-taking lag) and proactive interaction. Outperforms GPT-4o on vision benchmarks. Runs locally via llama.cpp & Ollama.

MiniCPM-o 4.5Real-time, full-duplex multimodal AI on your device
SERA is a family of open coding models (8B, 14B, 32B) trained with a new efficient method. SERA learns from "soft-verified" data, drastically reducing training costs. Easily adaptable to private codebases. Open weights, data & recipes.

SERAFast, accessible coding agents that adapt to any repo
Our SEO and GEO agent audits your site, uncovers high-impact SEO opportunities, and helps your brand show up in answers inside ChatGPT, Claude, Perplexity, and Grok.
Instead of guessing what to fix or spending months on random SEO tasks, the agent gives you clear, actionable opportunities and tracks how visible your brand is across both search engines and AI tools.

Okara SEO and GEO AgentAn agent that helps you rank on Google and in AI chatbots


