Search: github.com/babel | Heykuki News

Heykuki News

Top New Best Ask Show Jobs

Top New Best Ask Show Jobs

511.

Show HN: YoloAI: Sandboxed agent, no permission fatigue, diff/apply workflow (github.com/kstenerud)

1 point

3 months ago

512.

Show HN: Caelix, a balanced-ternary lattice field laboratory (caelix.co.uk)

1 point

3 months ago

513.

Show HN: SnapDrift – a simpler visual regression workflow for GitHub Actions (github.com/ranacseruet)

1 point

3 months ago

514.

Show HN: I built AgentSafety, an open benchmark for coding-agent safety (github.com/serkanaltuntas)

1 point

3 months ago

515.

Show HN: I over-engineered a home security camera that uses an LLM and talks (github.com/calz1)

1 point

3 months ago

516.

Show HN: ABES – a memory architecture for belief revision in AI agents (github.com/Aftermath-Technologies-Ltd)

1 point

3 months ago

517.

Show HN: Lila-E8 – 40M Parameter LLM with 0.37 Loss via E8 Lattice Attention

1 point

3 months ago

518.

Show HN: MSAM – Memory system for AI agents that knows when it doesn't know (github.com/jadenschwab)

1 point

3 months ago

519.

Show HN: MicroGPT-C – C99 GPT for Edge Training and Tiny Model Pipelines (github.com/enjector)

1 point

4 months ago

520.

How to Red Team Your AI Agent in 48 Hours – A Practical Methodology

1 point

4 months ago

521.

Show HN: AIOpt – local-only guardrail for LLM token/cost regressions (github.com/tkddlr0716-collab)

1 point

4 months ago

522.

Show HN: AI tool to that reaches top in machine-learning competition (github.com/pentoai)

1 point

4 months ago

523.

Show HN: WLM – A 70B model trained to decode "I'm fine" with 94.7% accuracy (github.com/gabewillen)

1 point

4 months ago

524.

Show HN: Oura (Activity Tracker) MCP Server with Claude

1 point

4 months ago

525.

Show HN: Bldr – polyglot build system for monorepos (github.com/GriffinCanCode)

1 point

5 months ago

526.

Show HN: Solving the H100 OOM Wall with CTDR – Maxwell Dashboard Included (github.com/Corusant-world)

1 point

5 months ago

527.

80.1 % on LoCoMo Long-Term Memory Benchmark with a pure open-source RAG pipeline

1 point

6 months ago

528.

Show HN: Beating SOTA embeddings on DeepMind's LIMIT benchmark (94% vs. 18%) (github.com/sangeet01)

1 point

6 months ago

529.

Show HN: Crunch – A Message Definition and Serdes Tool for Getting Things Right (github.com/sam-w-yellin)

1 point

6 months ago

530.

Show HN: EZTest – open-source alternative to TestRail/Testiny (github.com/houseoffoss)

1 point

6 months ago

531.

Show HN: Sigma Runtime ERI (v0.1) – Open benchmark for attractor-based LLMs (github.com/sigmastratum)

1 point

6 months ago

532.

Show HN: RankLens – Track your brand's visibility in AI answers reliably (seovendor.co)

1 point

6 months ago

533.

Looking for Open Source Co owners and decision makers

1 point

6 months ago

534.

Show HN: I built a triple-agent LLM system that verifies its own work

1 point

7 months ago

535.

Show HN: Exploring the limits of local LLM coding on consumer HW (github.com/lemonade-sdk)

1 point

8 months ago

536.

Show HN: Local RAG Eval Harness – reproducible benchmarksfor retrieval pipelines

1 point

myroslavmokhamm

8 months ago

537.

Show HN: Bloom – A Free Screen and Video Recording Software (thepublic.dev)

1 point

8 months ago

538.

Show HN: Hound – Relation-First Knowledge Graphs for Complex-System Reasoning (zenodo.org)

1 point

9 months ago

539.

Show HN: ARR-Medic-CYP3A4 – Open-Source Drug Interaction Toolkit (github.com/Flamehaven)

1 point

9 months ago

540.

Show HN: We made AI agents as simple as Laravel controllers (github.com/vizra-ai)

1 point

10 months ago