Search: github.com/reasonink | Heykuki News

Heykuki News

Top New Best Ask Show Jobs

Top New Best Ask Show Jobs

301.

Show HN: RAG chatbot using Qwen3 with custom thinking UI

4 points

a year ago

302.

Show HN: A CLI tool that stores Claude Code chats in your Git repo (github.com/Legit-Control)

4 points

5 months ago

303.

Show HN: A Vaadin Algebra and Calculus Solver Built with AI Assistance

4 points

3 months ago

304.

Show HN: Testronaut – AI-powered mission-based browser testing (testronaut.app)

4 points

9 months ago

305.

Show HN: Building the Missing Standard for Agentic Workflow Orchestration

4 points

a year ago

306.

Show HN: PearlOS: we gave AI a talking desktop environment instead of a text box

4 points

3 months ago

307.

Show HN: I built proxy that keeps RAG working while hiding PII

4 points

3 months ago

308.

Show HN: Locode, a local first CLI that routes tasks to local LLMs or Claude (github.com/chocks)

4 points

3 months ago

309.

Show HN: Claude-ts – Translation proxy to fix non-English token waste in Claude (github.com/kimi230)

4 points

3 months ago

310.

Show HN: NSED is public – Mixture-of-Models to Hit SOTA using self-hosted AI (github.com/peeramid-labs)

4 points

4 months ago

311.

Show HN: Agent Tinman – Autonomous failure discovery for LLM systems (github.com/oliveskin)

4 points

4 months ago

312.

Show HN: Forecaster Arena – Testing LLMs on real events with prediction markets (forecasterarena.com)

4 points

6 months ago

313.

Show HN: Beads Viewer (Bv) (github.com/Dicklesworthstone)

4 points

6 months ago

314.

Show HN: Agent Runner – open-source agent harness to benchmark real coding (designarena.ai)

4 points

6 months ago

315.

Show HN: Core – open-source memory graph for AI agents (88.24% SOTA on LoCoMo) (blog.heysol.ai)

4 points

9 months ago

316.

Show HN: GPT-5 vs. Claude 4 Sonnet on 200 Requests Benchmark (github.com/Cubent-Dev)

4 points

9 months ago

317.

Show HN: MALLM – A Multi-Agent Framework for Task Solving (github.com/Multi-Agent-LLMs)

4 points

a year ago

318.

Show HN: OSS's Answer to Cursor's Codebase Level Context for Large Projects (github.com/Bevel-Software)

4 points

a year ago

319.

Show HN: Plandex v2 – OSS AI coding agent w/ diff sandbox, full auto, 2M context (plandex.ai)

4 points

a year ago

320.

Show HN: I built an open-source vision RAG that embeds images and text together (docs.morphik.ai)

4 points

a year ago

321.

Show HN: Inferable – Build Reliable AI Agents with Durable Execution (github.com/inferablehq)

4 points

a year ago

322.

Show HN: Autopen, token-tree text editor that runs LLMs and shows probabilities (github.com/blackhole89)

4 points

a year ago

323.

Show HN: Chrome extension to run GenAI models in browser (github.com/tantara)

4 points

a year ago

324.

Show HN: Ameliorate – Analyze Debatable Problems (ameliorate.app)

4 points

2 years ago

325.

Show HN: Fragaria – From 'R's in Strawberry to Complex Problem-Solving AI (github.com/terraprompt)

4 points

2 years ago

326.

Show HN: Cognitive Language Agents (Executive Functions) (github.com/turing-machines)

4 points

2 years ago

327.

Show HN: Implementing CPU Logic into LLMs (github.com/turing-machines)

4 points

2 years ago

328.

Should LLMs ask "Is this real or fiction?" before replying to suicidal thoughts?

3 points

a year ago

329.

Show HN: Annotated Paper – Easily read, annotate, and understand research papers (annotatedpaper.khoj.dev)

3 points

a year ago

330.

Show HN: Underthreaded – The Brand for Engineers

3 points

2 years ago