1. Show HN: Give your agents a personal internet based on what you've surfed (github.com)
Shared memory for your team's coding agents. Contribute to Fergana-Labs/stash development by creating an account on GitHub.
2. Show HN: OldHand A Claude/Codex plugin to verify the development flow end-to-end (github.com)
Portable Codex and Claude skills for researched, minimal, end-to-end verified development workflows. - berwinsingh/oldhand
3. Show HN: I Repurposed Unit Tests to Show How Much Coding Agents "Improvise" (github.com)
Prompt based testing and coverage for high-velocity agentic coding. See how much your prompts are reflected in your agent's code using test coverage - RudderCode/Rudder
4. Show HN: FastStrapy – A create-next-app-inspired CLI for FastAPI (github.com)
A CLI tool to scaffold production-ready projects instantly — inspired by create-next-app, powered by Jinja2 templates and interactive prompts. - AnoopGeorge418/faststrapy
5. Show HN: I redesigned my self-hosted data manager's UI (4k stars, v2 (github.com)
Your web application for managing personal data. Contribute to Volmarg/personal-management-system development by creating an account on GitHub.
6. Show HN: Bean Network Tester – open-source bad network simulator (github.com)
Simulate bad network conditions on Windows - latency, packet loss, jitter, bandwidth limits, drops - to test how your app behaves on a poor connection. GUI + CLI, powered by WinDivert. - donislawde...
7. Show HN: BubbleHub - a local runtime and hosting for LLM agents (github.com)
BubbleHub is a runtime control layer for AI agents with sandboxing and local execution. - bublhub/BubbleHub
8. Show HN: Clayrune – Run Claude Code agents in parallel without losing context (github.com)
Open-source mission control for running multiple Claude Code agents across projects - one dashboard, a scheduler, cross-session memory, and browser/phone access. Runs locally on your own Claude sub...
9. Show HN: XTokenChecker – Verifies model identities of your AI gateway (xtokenchecker.com)
XTokenChecker is a public AI relay and model directory for comparing coverage, pricing, uptime, latency and real reviews.
13. Show HN: Listen to audiobooks like you read, at your own pace (listendock.com)
Sentence mode plays your audiobook one sentence at a time. Repeat a sentence, take time to think, and move on when you are ready, like reading a real book.
14. Show HN: The invisible WiFi man. How one man built global "Brand" WiFi in 2009 (calumbugattimacdonald.com)
15. Show HN: A speed reading test you can fail (www.readkinetic.com)
A two-minute reading test that measures you twice: once on the page, once with the words brought to you. Every score is multiplied by comprehension, so skimming scores nothing.
16. Show HN: Turn one plain-English question into a decision-ready market (researchmaster.ai)
Research Master turns topics, URLs, and files into verified market research for validation, competitor analysis, overseas markets, and source-backed decisions.
17. Show HN: Knuth–Plass algorithm for short-form video (viki.wiki)
18. Show HN: Clawx – A package manager where packages are agent tasks (github.com)
Run versioned, checksummed and approval-gated tasks with Claude Code, Codex, Gemini and other agent CLIs. - debarshibasak/clawx
19. Show HN: Lex – a calm language-learning toolkit for 34 languages (lex.school)
A calm workspace for learning languages by reading, writing, and building your own vocabulary. AI essay feedback, leveled reading, spaced repetition — 34 languages. Free 3-day trial, no card required.