Search: github.com/reasonink | Heykuki News

HK

Heykuki News

Top New Best Ask Show Jobs

Top New Best Ask Show Jobs

301.

Forked CozoDB to give agents cognitive primitives

3 days ago

5 points

302.

Show HN: The Order of the Agents – Make Codex and Claude Create the Perfect PRD

github.com/btahir

2 months ago

5 points

303.

Show HN: TypeGraph – Type-safe graphs on Postgres/SQLite (no graph DB required)

4 months ago

5 points

304.

Show HN: Store whatever you decide to remember

github.com/NevaMind-AI

5 months ago

5 points

305.

Show HN: Decision Guardian – Enforce ADRs on PRs

4 months ago

4 points

306.

Show HN: AI Paul Graham

paulgraham-nia.com

7 months ago

4 points

307.

Show HN: SageOx – The Hivemind for Agentic Engineering

4 months ago

4 points

308.

Show HN: Project Chimera – Hybrid AI Agent Combining LLM, Symbolic, and Causal

github.com/akarlaraytu

9 months ago

4 points

309.

Show HN: RAG chatbot using Qwen3 with custom thinking UI

a year ago

4 points

310.

Show HN: A CLI tool that stores Claude Code chats in your Git repo

github.com/Legit-Control

5 months ago

4 points

311.

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

4 months ago

4 points

312.

Show HN: Testronaut – AI-powered mission-based browser testing

10 months ago

4 points

313.

Show HN: Building the Missing Standard for Agentic Workflow Orchestration

a year ago

4 points

314.

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

3 months ago

4 points

315.

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

3 months ago

4 points

316.

Show HN: Locode, a local first CLI that routes tasks to local LLMs or Claude

github.com/chocks

3 months ago

4 points

317.

Show HN: Claude-ts – Translation proxy to fix non-English token waste in Claude

github.com/kimi230

4 months ago

4 points

318.

Show HN: NSED is public – Mixture-of-Models to Hit SOTA using self-hosted AI

github.com/peeramid-labs

4 months ago

4 points

319.

Show HN: Agent Tinman – Autonomous failure discovery for LLM systems

github.com/oliveskin

5 months ago

4 points

320.

Show HN: Forecaster Arena – Testing LLMs on real events with prediction markets

forecasterarena.com

6 months ago

4 points

321.

Show HN: Beads Viewer (Bv)

github.com/Dicklesworthstone

7 months ago

4 points

322.

Show HN: Agent Runner – open-source agent harness to benchmark real coding

7 months ago

4 points

323.

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

10 months ago

4 points

324.

Show HN: GPT-5 vs. Claude 4 Sonnet on 200 Requests Benchmark

github.com/Cubent-Dev

10 months ago

4 points

325.

Show HN: MALLM – A Multi-Agent Framework for Task Solving

github.com/Multi-Agent-LLMs

a year ago

4 points

326.

Show HN: OSS's Answer to Cursor's Codebase Level Context for Large Projects

github.com/Bevel-Software

a year ago

4 points

327.

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

a year ago

4 points

328.

Show HN: I built an open-source vision RAG that embeds images and text together

docs.morphik.ai

a year ago

4 points

329.

Show HN: Inferable – Build Reliable AI Agents with Durable Execution

github.com/inferablehq

a year ago

4 points

330.

Show HN: Autopen, token-tree text editor that runs LLMs and shows probabilities

github.com/blackhole89

a year ago

4 points