OSINTech's Timeline (178) - 03.09.2026

OSINTech published its weekly curated roundup of OSINT, security research, and AI tools for the week of 28 August to 3 September 2026. The list highlights projects including h5i, a Rust-based auditable browser for AI agents that claims roughly 3x faster performance and 86% less peak memory than headless Chromium, GuppyLM, a ~9M parameter LLM, and AIPass, a persistent agent workspace. Other entries include the Tare AI-powered browser, fcc-model-check for validating model routing, and a local Claude Code plus Ollama setup guide.

Life Week of 28 August — 3 September 2026 Every week, I manually curate tools, research, and services that are genuinely useful for OSINT, digital investigations, security research, and adjacent fields. No hype. No SEO noise. No “AI startups that change everything”. Only things you can open, verify, and actually use . 🧭 Featured Projects Get SMS Online has been providing temporary phone numbers for SMS verification since 2016. Our service lets you receive SMS online and verify accounts on more than 700 popular websites and apps, including social media platforms, email providers, messaging apps, online marketplaces, dating services, and much more: Cyb Detective’s Substack. Every day about OSINT Open Source Intelligence tools and techniques: Your project can be featured here. To collaborate, please send me a private message: OSINTech https://open.substack.com/users/237870133-osintech?utm source=mentions 🌍 Regional & Thematic OSINT Verification Toolset by Julia Bayer: 🔗 https://start.me/p/ZGAzN7/verification-toolset https://start.me/p/ZGAzN7/verification-toolset fcc-model-check is a Bash health-check utility for validating model routing between Free Claude Code FCC with NVIDIA NIM and other models: 🔗 https://github.com/bormaxi8080/fcc-model-check https://github.com/bormaxi8080/fcc-model-check Claude Code + Ollama Local Setup. Run Claude Code locally with Ollama on Windows, with a simple launcher, setup guide, and CPU/GPU troubleshooting notes: 🔗 https://github.com/emilycodes-cmd/claude-code-ollama-local https://github.com/emilycodes-cmd/claude-code-ollama-local Awesome Workflow Automation A curated list of Workflow Automation Software, Engines and Tools: 🔗 https://github.com/dariubs/awesome-workflow-automation https://github.com/dariubs/awesome-workflow-automation 🛠 OSINT Tools, Services & Investigations Tare is a modern AI-powered browser built with Electron and React, combining fast web browsing, intelligent chat, page understanding, and automation tools in one lightweight desktop client: 🔗 https://github.com/hezongxi/Tare https://github.com/hezongxi/Tare h5i. Secure, auditable browser for AI agents. Pure Rust, no Chromium or V8. ~3× faster and ~86% less peak memory than headless Chromium: 🔗 https://github.com/h5i-dev/h5i https://github.com/h5i-dev/h5i IWA Chrome. Undetectable offensive toolkit inside Chrome: 🔗 https://github.com/CICADA8-Research/iwa-tools https://github.com/CICADA8-Research/iwa-tools Mailflare. Email client with custom domain based on Cloudflare: 🔗 https://github.com/hieunc229/mailflare https://github.com/hieunc229/mailflare Lonkero. Wraps around your attack surface. Professional-grade scanner for real penetration testing. Fast. Modular. Rust: 🔗 https://github.com/bountyyfi/lonkero https://github.com/bountyyfi/lonkero Medusa is a speedy, parallel, and modular, login brute-forcer: 🔗 https://github.com/jmk-foofus/medusa https://github.com/jmk-foofus/medusa iOS OCR Server. An iOS OCR Server Using Apple’s Vision Framework: 🔗 https://github.com/riddleling/iOS-OCR-Server https://github.com/riddleling/iOS-OCR-Server 🤖 Universal Search & AI GuppyLM. A ~9M parameter LLM that talks like a small fish: 🔗 https://github.com/arman-bd/guppylm https://github.com/arman-bd/guppylm Antology Atlas. Understand what your codebase builds, why it is structured that way, and what a change could affect. One shared Markdown ontology for humans and coding agents—visualized for people, accessible to agents through MCP, and reviewed with Git. Local-first. Open source: 🔗 https://github.com/wlsdks/ontology-atlas https://github.com/wlsdks/ontology-atlas AIPass. Persistent Agent Workspace - AI agents that remember, collaborate, and never start from zero: 🔗 https://github.com/AIOSAI/AIPass https://github.com/AIOSAI/AIPass Claude Meter. macOS menu bar app for tracking Claude.ai plan usage in real-time. Monitor 5-hour session, 7-day weekly, and Sonnet-specific limits with color-coded indicators and smart notifications: 🔗 https://github.com/eddmann/ClaudeMeter https://github.com/eddmann/ClaudeMeter Claude Rank. AI Readiness and Search Visibility scanner for Claude Code. Find out if AI engines can discover, crawl, and cite your site - then fix what’s blocking them: 🔗 https://github.com/Houseofmvps/claude-rank https://github.com/Houseofmvps/claude-rank Antigravity CLI brings the reasoning, execution, and orchestration capabilities of Antigravity agent harness directly into your terminal: 🔗 https://github.com/google-antigravity/antigravity-cli https://github.com/google-antigravity/antigravity-cli Apache Maka Incubating is a local-first AI agent workspace. Model messages, tool calls, tool results, permission decisions, and termination events are recorded as an append-only log: 🔗 https://github.com/apache/maka https://github.com/apache/maka Sim is the collaborative workspace to build, deploy, and monitor AI agents and workflows. Used by 100,000+ builders: 🔗 https://github.com/simstudioai/sim https://github.com/simstudioai/sim Claudish To English. A Claude Code plugin that shows a plain-English rewrite of each assistant message, produced by a local LLM via ollama default , the codex CLI , the Anthropic API , or any OpenAI-compatible API . It is display-only : Claude’s own reasoning and the saved transcript keep the original text - only what you read on screen changes: 🔗 https://github.com/gvzdv/claudish-to-english https://github.com/gvzdv/claudish-to-english iFixAI. Independent Auditing of AI Agents. Run by human or the agent itself, to answer the most crucial question in the AI Agent Economy. Is the agent doing what is supposed to do? With iFixAi you can have this answer in less than 120 seconds: 🔗 https://github.com/ifixai-ai/iFixAi https://github.com/ifixai-ai/iFixAi ZG. ZvecGrep is a Local-first search across your workspace, built for humans and AI agents: 🔗 https://github.com/zvec-ai/zvec-grep https://github.com/zvec-ai/zvec-grep Cate. An infinite zoomable canvas for coding. Editor, terminal, and browser panels in a spatial workspace: 🔗 https://github.com/0-AI-UG/cate https://github.com/0-AI-UG/cate Inferoa. Inference-native Tokenmaxxing Agent Harness for Loop Engineering: 🔗 https://github.com/agentic-in/inferoa https://github.com/agentic-in/inferoa LatticeDB. Embedded single-file knowledge graph database with vector search and full-text search for AI/RAG apps: 🔗 https://github.com/jeffhajewski/latticedb§ https://github.com/jeffhajewski/latticedb%C2%A7 👨💻 Software Development & APIs Vite. Next generation frontend tooling: 🔗 https://github.com/vitejs/vite https://github.com/vitejs/vite Mitosis. Write components once, run everywhere. Compiles to React, Vue, Qwik, Solid, Angular, Svelte, and more: 🔗 https://github.com/BuilderIO/mitosis https://github.com/BuilderIO/mitosis Herm. Terminal-native AI coding agent running in containers: 🔗 https://github.com/aduermael/herm https://github.com/aduermael/herm Mekka. Experimental source-available SQLite/libSQL backend for human-and-agent-native workflows, with Studio and scoped MCP access: 🔗 https://github.com/yiaany/Mekka https://github.com/yiaany/Mekka Zedis. A blazing-fast, native Redis GUI built with Rust and GPUI: 🔗 https://github.com/vicanso/zedis https://github.com/vicanso/zedis 🐧 Linux & DevOps WailBrew. Minimalistic Homebrew GUI made with Go, Wails and React: 🔗 https://github.com/wickenico/WailBrew https://github.com/wickenico/WailBrew Sniffnet. Comfortably monitor your network traffic: 🔗 https://github.com/GyulyVGC/sniffnet https://github.com/GyulyVGC/sniffnet Sync-in Server. Sovereign platform for file storage, sharing, synchronization, and collaboration: 🔗 https://github.com/Sync-in/server https://github.com/Sync-in/server mirrord. Run any process, on your machine or in an AI agent’s environment, as if it were a pod in your Kubernetes cluster: real env vars, DNS, network, traffic: 🔗 https://github.com/metalbear-co/mirrord https://github.com/metalbear-co/mirrord 🔌 Hardware & Devices DroneSploit. This CLI framework is based on sploitkit and is an attempt to gather hacking techniques and exploits especially focused on drone hacking . For the ease of use, the interface has a layout that looks like Metasploit: 🔗 https://github.com/dronesploit/dronesploit https://github.com/dronesploit/dronesploit 🚨 From CyberDetective AIRCRAFTDEFECTS. 1,757,827 Federal Aviation Administration service difficulty reports archive 1995-01-01 to 2026-08-26 with infographics and detailed statistics: 🔗 https://aircraftdefects.com/ https://aircraftdefects.com/ 📌 Where to Follow - LinkedIn: https://www.linkedin.com/in/osintech/details/featured/ https://www.linkedin.com/in/osintech/details/featured/ If this timeline saves you time, it’s doing its job. Free to read. Manually curated. Minimal noise. 📌 Legal and ethical note All tools and techniques documented in the dataset are presented for informational, educational and information security purposes only. The dataset does not promote or endorse illegal activities. Users are responsible for complying with applicable laws and ethical standards. 📌 About future updates The dataset is updated on a regular basis. Future posts will document changes, notable additions and emerging trends observed within the dataset. This post serves as an introduction and reference point for those updates.