Search: github.com/rdegges | Heykuki News

HK

Heykuki News

Top New Best Ask Show Jobs

Top New Best Ask Show Jobs

151.

Show HN: git-lrc – Free, Micro AI Code Reviews That Run on Git Commit

github.com/HexmosTech

6 days ago

9 points

152.

A general purpose library for C

7 years ago

8 points

153.

Show HN: WhiskeySour – A 10x faster drop-in replacement for BeautifulSoup

2 months ago

8 points

154.

Show HN: Telemetry – Predict when you'll reach your goals

telemetry.software

3 years ago

7 points

155.

Show HN: MCPSpec – Ship reliable MCP servers without writing test code

light-handle.github.io

4 months ago

7 points

156.

Show HN: Claumon – forecasting Claude Code usage limits with a Gamma process

github.com/fabioconcina

12 days ago

7 points

157.

Show HN: Agentic AI Frameworks on AWS (LangGraph,Strands,CrewAI,Arize,Mem0)

github.com/aws-samples

a year ago

7 points

158.

Show HN: DataForge Core – Pure functional SQL data transforms

github.com/dataforgelabs

2 years ago

7 points

159.

Show HN: 20x – Open-source agent orchestrator for Linear/HubSpot tasks

github.com/peakflo

4 months ago

6 points

160.

Show HN: mcp-recorder – VCR.py for MCP servers. Record, replay, verify

github.com/devhelmhq

4 months ago

6 points

161.

Show HN: Shortest, a natural language AI-powered testing framework

github.com/anti-work

a year ago

6 points

162.

Show HN: Scope-structured arena memory for C, O(1) cleanup, no GC/borrow checker

github.com/hollow-arena

2 months ago

5 points

163.

Show HN: 70 days, 800 stars. If AI bugs are not random but math inevitable?

github.com/onestardao

10 months ago

5 points

164.

Show HN: PreflightLLMCost – Try to Predict LLM API Costs Before Execution

github.com/aatakansalar

a year ago

5 points

165.

Show HN: Arch-Function: 3B parameter LLM that beats GPT-4o on function calling

2 years ago

5 points

166.

Show HN: I benchmarked LLM agents on fixing real-world security vulnerabilities

giovannigatti.github.io

18 days ago

4 points

167.

Show HN: AgentCheck – Local AI-powered code review agents for Claude Code

github.com/devlyai

10 months ago

4 points

168.

Show HN: CLI for scoring OpenAPI for LLM legibility

github.com/jentic

18 days ago

seanblanchfield

4 points

169.

Show HN: LLM Council – Run multiple LLMs with critique and consensus eval

github.com/abhishekgandhi-neo

4 months ago

4 points

170.

Show HN: Lightbox – Flight recorder for AI agents (record, replay, verify)

uselightbox.app

5 months ago

4 points

171.

Show HN: 1.5B LLM routing model that aligns to preferences, not leaderboards

a year ago

honorable_coder

4 points

172.

Show HN: Empirical – test framework for JavaScript developers building with LLMs

github.com/empirical-run

2 years ago

4 points

173.

Show HN: Jitar, a runtime that automates all end-to-end communication for TS

github.com/MaskingTechnology

3 years ago

4 points

174.

Show HN: OctoFlow – A GPU-native programming language

4 months ago

3 points

175.

Show HN: Saguaro: CLI that makes Claude Code fix its own mistakes

github.com/mesa-dot-dev

3 months ago

3 points

176.

Show HN: A Geometric Algebra NN Framework (100% on 13-hop reasoning)

github.com/Concode0

3 months ago

3 points

177.

Tq-KV – Rust implementation of TurboQuant that works on GGUF models

3 months ago

3 points

178.

Show HN: CBrowser – Simulate how a confused first-timer experiences your website

github.com/alexandriashai

4 months ago

3 points

179.

Show HN: Cobalt – Unit tests for AI agents, like Jest but for LLMs

github.com/basalt-ai

4 months ago

3 points

180.

Show HN: TITO – Automated threat modeling from code (open source)

github.com/Leathal1

5 months ago

3 points