Search: github.com/eval | Heykuki News

HK

Heykuki News

Top New Best Ask Show Jobs

Top New Best Ask Show Jobs

961.

Show HN: Smart GitHub Contribution Tracker – Fair analysis beyond line counts

github.com/kyliemckinleydemo

7 months ago

2 points

962.

Show HN: Superpipe – optimized LLM pipelines for structured outputs

github.com/villagecomputing

2 years ago

2 points

963.

Show HN: Compare AutoML frameworks on 10 Tabular Kaggle competitions

5 years ago

2 points

964.

Show HN: Deploy your docker-compose stack with Helm

6 years ago

2 points

965.

Ask HN: Angular2 UI Frameworks ng-bootstrap, ng2-bootstrap or material2

10 years ago

2 points

966.

UK government built an AI tool to digitise historic planning records

8 days ago

2 points

967.

Show HN: Pantheon – AI vs AI: one writes the code, the other attacks it

github.com/lolu1032

10 days ago

2 points

968.

Show HN: Interactive first-principles climate physics simulation with explainer

earth.crackalamoo.com

a month ago

2 points

969.

Show HN: Darc – grep-like memory search tool for coding agents

github.com/0xjunha

a month ago

2 points

970.

Show HN: Elmo (Open Source AEO)

github.com/elmohq

a month ago

2 points

971.

Show HN: Markanywhere – A Streaming Processor of Meanings

github.com/xemantic

a month ago

2 points

972.

Show HN: Lilith-zero update: fast Rust security for agents

github.com/BadC-mpany

2 months ago

2 points

973.

Show HN: JSON-logic-path – JSON logic with jsonpath multi-value resolution

github.com/bayinfosys

2 months ago

2 points

974.

Show HN: Springdrift – A persistent runtime for long-lived LLM agents

github.com/seamus-brady

2 months ago

2 points

975.

Show HN: Evo – parallel autoresearch experiments for Claude Code and Codex

github.com/evo-hq

2 months ago

2 points

976.

Show HN: OpenParallax: OS-level privilege separation for AI agent execution

2 months ago

2 points

977.

Show HN: Girlfriend in CLI – AI-native persona harness for social training

github.com/NomaDamas

2 months ago

2 points

978.

Show HN: Lodmem – Level of Detail Context Management for Agents

github.com/agenteractai

2 months ago

2 points

979.

Show HN: SkillCompass – Diagnose and Improve AI Agent Skills Across 6 Dimensions

github.com/Evol-ai

3 months ago

2 points

980.

Show HN: OpenClaw Arena – Benchmark models on real tasks, rank by perf and cost

3 months ago

2 points

981.

Show HN: Image Ranker – Open-Source Pairwise Ranking for Preference Learning

github.com/QuentinWach

3 months ago

2 points

982.

Show HN: Tested 12 LLMs with few-shot examples

3 months ago

2 points

983.

Show HN: Perstack – Containerized harness, 5 tests with full logs and API cost

github.com/perstack-ai

3 months ago

2 points

984.

Show HN: LocalAgent v0.5.0, a local-first Rust agent runtime

github.com/CalvinSturm

3 months ago

2 points

985.

Show HN: A test harness that blocks unsafe AI actions before execution

3 months ago

celestinestudio

2 points

986.

Show HN: Wikimetron – Surface hidden sensitivity and risk in Wikipedia

github.com/opinionscience

3 months ago

2 points

987.

Show HN: HDC-based function caller ranks #2 on BFCL V4 – $2.08 vs. Opus at $87

github.com/glyphh-ai

3 months ago

2 points

988.

Show HN: AlphaEvolve inspired evolution harness for Pokemon

github.com/papercomputeco

4 months ago

2 points

989.

Show HN: Aegis – Open-source pre-execution firewall for AI agents

github.com/Justin0504

4 months ago

2 points

990.

Show HN: Yardstiq – Compare LLM outputs side-by-side in your terminal

4 months ago

2 points