OpenClix, Agent friendly, open-source retention tooling
Hi HN, I’m sharing OpenClix, an open source toolkit for running mobile engagement and retention flows directly inside your app. The motivation came from repeatedly seeing the same pattern when teams try to improve retention. They end up stitching together push providers, experimentation tools, analytics pipelines, and backend services just to ship simple onboarding nudges or re engagement reminders. The setup becomes complex very quickly. OpenClix takes a different approach. Instead of a hosted platform or heavy SDK, it provides config driven engagement logic that runs on device. Campaigns…
What it does
In the maker’s words, at launch
Hi HN, I’m sharing OpenClix, an open source toolkit for running mobile engagement and retention flows directly inside your app. The motivation came from repeatedly seeing the same pattern when teams try to improve retention. They end up stitching together push providers, experimentation tools, analytics pipelines, and backend services just to ship simple onboarding nudges or re engagement reminders. The setup becomes complex very quickly. OpenClix takes a different approach. Instead of a hosted platform or heavy SDK, it provides config driven engagement logic that runs on device. Campaigns and rules live in a simple JSON config and react to app events locally. You can trigger notifications, schedule follow ups, or suppress messages based on user behavior without needing a backend control plane. A few core ideas behind the project: • Local first execution. Engagement logic runs on the device, which removes a lot of infrastructure and latency. • Source vendoring instead of SDK lock in. The code can live directly in your repo so you can inspect and modify it. • Config driven campaigns. Triggers, guardrails, and messaging logic are defined in a simple config file. • Agent friendly workflows. The project is structured so coding agents can safely generate and modify campaigns or rules. Typical things people use it for: • onboarding nudges • streak or habit reminders • re engagement after inactivity • retention experiments without a full growth stack I’d love feedback on a few things: • Does the local first approach make sense for engagement logic? • What types of campaigns would you want to run this way? • What analytics or integrations would make this more useful? Happy to answer questions and discuss how others handle retention tooling today.
Does the same job
all alternatives →
- NONous – Open-Source Agent Framework with Autonomous, SWE Agents, WebUI2024 · github.com · ▲155
Hello HN! The day has finally come to stop adding features and start sharing what I've been building the last 5-6 months. It's a bit of CrewAI, OpenDevon, LangFuse/Cloud all in one, providing devs who prefer TypeScript an integrated framework thats provides a lot out of the box to start experimenting and building agents with. It started after peeking at the LangChain docs a few times and never liking the example code. I began experimenting with automating a simple Jira request from the engineering team to add an index to one of our Google Spanner databases (for context I'm the…
- RARemuda, a CLI Agent OrchestratorJun 2026 · github.com · ▲5
Hi HN, I recently open sourced a small tool (Remuda) that I built at work to remove some of the friction of launching and managing agents and figured HN might be interested. I also wrote a post on the company blog that goes into more detail about why I built it and showcases its features: https://www.yendo.com/blog/remuda-an-agent-orchestrator
- OSOpenSkills – Stop bloating your LLM context with unused instructionsJan 2026 · ▲9
Hello HN, I’ve been building AI agents lately and ran into a common "Context Bloat" problem. When an agent has 20+ skills, stuffing every system prompt, reference doc, and tool definition into a single request quickly hits token limits and degrades model performance (the "lost in the middle" problem). To solve this, I built OpenSkills, an open-source SDK that implements a Progressive Disclosure Architecture for agent skills. The Core Concept: Instead of loading everything upfront, OpenSkills splits a skill into three layers: Layer 1 (Metadata): Light-weight tags and triggers (always loaded…
- TTTrack Token usage for major platforms,know your token flowJul 2026 · lifehacksgermany.com · ▲5
I use multiple AI tools for work and also my side projects, and the annoying part was to track my costs and token usage across tools. Everytime I had to visit each tool and its respective usage setting to check it and I was losing patience and also was getting hit by surprise limits Now I know that there are already free/open-source trackers for Cursor or Claude usage, and they are useful if that is all you need. My problem is broader as I wanted one small place to see tokens, spend, subscriptions and limits across the AI tools I actually use. I was really tired of switching tabs and…
- ARAgents, run any coding agent on your subscription not API costsMay 2026 · agents-cli.sh · ▲6
Hi HN. I'm the founder of Phoenix Labs (ex TikTok, Applied AI) and we're open sourcing our internal tooling today which is like a toolchain / meta-harness for CLI agents useful for really scaling eng and creative work. We are a very small team who's building a very ambitious product so we had to find ways to squeeze every ounce of efficiency that we could get our hands on. Harness strengths of different models (Claude, GPTs) and CLI-harnesses (Claude Code, Codex), safe/robust browser integration to speed up UX/QA testing, teams cli to speed up security reviews and parallelize…
More ai this month
the category →
I trained a 125M-parameter transformer to autocomplete piano performances in real time (~108 notes/sec on an iPhone 15). The idea is basically GitHub Copilot or Tabnine, except instead of prompting it with code, you prompt it by playing a few notes on a MIDI piano. The model then continues what you played, entirely on-device. The app is free if anyone wants to try it. Happy to answer questions about the model, training, Core ML, or the many things that didn't work.
AI · 17d ago · simedw.com
Astute▲585Automate your B2B brand going viral, with new media creators
AI · 18d ago · company-app.joinastute.com
Hey HN, Henry from Cactus here! We previously released Cactus Needle, a 14MB agentic LLM for tool call, device use, and structured extraction for phones, wearables, smart homes, small robots and microcontrollers. We got really great feedback here, and have now incorporated the suggestions to release Needle 2. The whole model is a single 14MB binary that runs a full session in 28MB of RAM; 45m parameters at 2bit compression. Needle hits 500 tokens/sec decode speed on a Raspberry Pi 5, sits between 400-1,500 tokens/sec on VR devices like Meta Quest 3S and Apple Vision Pro, and ranges…
AI · 26d ago · cactuscompute.com
Launched alongside, March 2026
the whole month →
Switch from ChatGPT to Claude with import memory feature
AI · Mar 2026 · claude.com
