Search: github.com/babel | Heykuki News

HK

Heykuki News

Top New Best Ask Show Jobs

Top New Best Ask Show Jobs

511.

Show HN: TideSurf – Your agent doesn't need eyes to browse the web

3 months ago

1 points

512.

Show HN: Detect Drift in TypeScript codebases

github.com/LogicStamp

3 months ago

1 points

513.

Show HN: Drift-guard – Protect your UI from AI agents' design drift

3 months ago

1 points

514.

Show HN: YoloAI: Sandboxed agent, no permission fatigue, diff/apply workflow

github.com/kstenerud

3 months ago

1 points

515.

Show HN: Caelix, a balanced-ternary lattice field laboratory

3 months ago

1 points

516.

Show HN: SnapDrift – a simpler visual regression workflow for GitHub Actions

github.com/ranacseruet

3 months ago

1 points

517.

Show HN: I built AgentSafety, an open benchmark for coding-agent safety

github.com/serkanaltuntas

4 months ago

1 points

518.

Show HN: I over-engineered a home security camera that uses an LLM and talks

github.com/calz1

4 months ago

1 points

519.

Show HN: ABES – a memory architecture for belief revision in AI agents

github.com/Aftermath-Technologies-Ltd

4 months ago

1 points

520.

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

4 months ago

1 points

521.

Show HN: MSAM – Memory system for AI agents that knows when it doesn't know

github.com/jadenschwab

4 months ago

1 points

522.

Show HN: MicroGPT-C – C99 GPT for Edge Training and Tiny Model Pipelines

github.com/enjector

4 months ago

1 points

523.

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

4 months ago

1 points

524.

Show HN: AIOpt – local-only guardrail for LLM token/cost regressions

github.com/tkddlr0716-collab

4 months ago

1 points

525.

Show HN: AI tool to that reaches top in machine-learning competition

github.com/pentoai

5 months ago

1 points

526.

Show HN: WLM – A 70B model trained to decode "I'm fine" with 94.7% accuracy

github.com/gabewillen

5 months ago

1 points

527.

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

5 months ago

1 points

528.

Show HN: Bldr – polyglot build system for monorepos

github.com/GriffinCanCode

5 months ago

1 points

529.

Show HN: Solving the H100 OOM Wall with CTDR – Maxwell Dashboard Included

github.com/Corusant-world

6 months ago

1 points

530.

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

6 months ago

1 points

531.

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

github.com/sangeet01

6 months ago

1 points

532.

Show HN: Crunch – A Message Definition and Serdes Tool for Getting Things Right

github.com/sam-w-yellin

6 months ago

1 points

533.

Show HN: EZTest – open-source alternative to TestRail/Testiny

github.com/houseoffoss

7 months ago

1 points

534.

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

github.com/sigmastratum

7 months ago

1 points

535.

Show HN: RankLens – Track your brand's visibility in AI answers reliably

7 months ago

1 points

536.

Looking for Open Source Co owners and decision makers

7 months ago

1 points

537.

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

8 months ago

1 points

538.

Show HN: Exploring the limits of local LLM coding on consumer HW

github.com/lemonade-sdk

8 months ago

1 points

539.

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

8 months ago

myroslavmokhamm

1 points

540.

Show HN: Bloom – A Free Screen and Video Recording Software

9 months ago

1 points