Search: github.com/aryx | Heykuki News

HK

Heykuki News

Top New Best Ask Show Jobs

Top New Best Ask Show Jobs

301.

Show HN: Synapse – structurally honest reasoning VM (spec) – the missing layer

github.com/nienso

4 months ago

1 points

302.

Show HN: Engram update – 92% DMR, hosted API, lessons shipping agent memory

github.com/tstockham96

4 months ago

1 points

303.

Show HN: Benchmarking the Keep memory system with LoCoMo

4 months ago

1 points

304.

Show HN: Engram – Memory for AI coding agents (2.5K installs, 80% on LOCOMO)

4 months ago

1 points

305.

Show HN: Aerial-autonomy-stack–Simulate and Deploy Perception-based Drones

github.com/JacopoPan

4 months ago

SufficientFix42

1 points

306.

Show HN: Agent Hypervisor – Reality Virtualization for AI Agents

github.com/sv-pro

4 months ago

1 points

307.

Show HN: SuperLocalMemory– Local-first AI memory for Claude, Cursor and 16+tools

github.com/varun369

4 months ago

1 points

308.

MiRAGE: Open-source framework for multimodal RAG evaluation

4 months ago

1 points

309.

Show HN: Open-source PaperBanana – academic diagrams from text via agents

github.com/llmsresearch

5 months ago

1 points

310.

Show HN: A verified foundation of mathematics in Coq (Theory of Systems)

5 months ago

1 points

311.

Show HN: Infinate –O(k)constant-time spatial attention for unlimited LLM context

github.com/ch1pu

5 months ago

1 points

312.

Subject-based weight routing for LLMs (27 days before DeepSeek Engram)

5 months ago

1 points

313.

Show HN: DR Web Engine – JSON-based web scraping that doesn't break on change

github.com/starlitlog

6 months ago

1 points

314.

Show HN: DataFlow – Open Tool for LLM data prep 10k synthetic > 1M generic data

github.com/OpenDCAI

6 months ago

1 points

315.

Show HN: QCMP Framework for Poison-Resistant AI Agents [pdf]

github.com/bradmcevilly

6 months ago

1 points

316.

StillMe – an open-source "transparent RAG" framework

6 months ago

1 points

317.

Show HN: LimiX-2M – The super-light foundation model redefining tabular learning

7 months ago

1 points

318.

Show HN: CellARC Measuring Intelligence with Cellular Automata

7 months ago

1 points

319.

Show HN: Transfer Learning Boosts GQE Accelerating Drug Discovery in the NISQEra

8 months ago

1 points

320.

Agentic web browsing can't scale with cloud LLMs

8 months ago

1 points

321.

Show HN: Bibfixer – AI-powered BibTeX cleaner

github.com/takashiishida

9 months ago

1 points

322.

Show HN: SyGra – Graph-oriented Synthetic data generation Pipeline for LLMs

github.com/ServiceNow

9 months ago

1 points

323.

Show HN: Arch-Router – Aligning LLM Routing with Human Preferences

a year ago

honorable_coder

1 points

324.

Show HN: BMP – Fast, Exact Learned Sparse Retrieval for RAG

github.com/pisa-engine

a year ago

1 points

325.

Responsible Prompting API – open-source project – Feedback appreciated

a year ago

1 points

326.

Show HN: Tokenkit – Convert LLMs to new tokenizers (incl byte-level Llama/Gemma)

github.com/bminixhofer

a year ago

1 points

327.

Show HN: ResearchU – AI-Powered Research Assistant

research-u.vercel.app

a year ago

1 points

328.

Show HN: AiLert – Open-Source AI Newsletter Engine in Python

github.com/anuj0456

a year ago

1 points

329.

Show HN: PyPI Scout – Find Python packages on PyPI using vector embeddings

github.com/fpgmaas

2 years ago

1 points

330.

Show HN: Neuroscience-inspired interpretation of how Transformers work

github.com/tfburns

2 years ago

1 points