HN Explorer

everlier

↗ HN profile [ 137 ms ] full profile
Karma
0
Created
()
Submissions
0
  1. Agent Swarms (av.codes)
    1 points 0
  2. A Harness for AGI (viktor.com)
    2 points 0
  3. Harness Archaeology (av.codes)
    2 points 0
  4. Local Inference (av.codes)
    5 points 0
  5. 1 points 0
  6. Show HN: Harbor v0.4.19 – harbor launch –back end vLLM –web codex (github.com)
    4 points 0
  7. Show HN: Naiou – an agent that can only answer yes or no to your query (github.com)

    Visuals are arguably the most interesting part, demo in action here: https://www.youtube.com/watch?v=bLImeRP94OY This is just a fun side project, but it is still a fully functional agent with read-only access to your…

    1 points 0
  8. Skilled – a CLI and TUI to inspect skill usage by your coding agents (github.com)
    1 points 1
  9. Show HN: Tiny agentic loop with Docker sandbox (github.com)

    New in mi v1.7.5: "--sandbox" runs the agent inside Docker with your current directory mounted, to contain the blast radious in case of unexpected attacks. mi Works with any OpenAI-compatible model (including local…

    1 points 0
  10. Show HN: [Video] Tribute to LLM releases in April 2026 (youtube.com)
    2 points 0
  11. Show HN: Replacing spec-driven development with just facts (github.com)

    I had a lot of issues with spec-driven approaches, agents are too readily producing fluff, large projects have so many specs agents start making mistakes maintaining them. There's a constant consistency tax. In the end…

    7 points 4
  12. Hyperscalers are 4500 years old (av.codes)
    2 points 1
  13. The Gate Test: Why Human-in-the-Loop Fails and How to Fix It (jitera.com)
    6 points 0
  14. 1 points 0
  15. Mi – agentic harness in 30 lines of JavaScript (github.com)
    3 points 1
  16. The Quality Wall of AI Adoption (jitera.com)
    1 points 2
  17. Show HN: AI for Your Team (jitera.com)

    The product was there for the past two years, but we're only now approaching a release on global market. In a nutshell, it's a workspace for non-technical people to work with AI without forcing anyone at the hard end of…

    1 points 0
  18. Interface Hall of Shame (1999) (hallofshame.gp.co.at)
    4 points 0
  19. A History of Local LLMs (av.codes)
    4 points 0
  20. 40 Months of Prompt Injection (openguard.sh)
    4 points 1
  21. There Is No Firewall for English (openguard.sh)
    7 points 0
  22. The Webpage Has Instructions. The Agent Has Your Credentials (openguard.sh)
    37 points 9
  23. Show HN: A single CLI to manage llama.cpp/vLLM/Ollama models (github.com)

    Harbor crossed its 127th (next one is special) release. One notable added feature is ability to manage all my LLMs with a single CLI. # list all models harbor ls # pairs well with jq harbor ls --json # Ollama harbor…

    2 points 2
  24. Show HN: OpenGuard (openguard.sh)
    1 points 0
  25. 1 points 0