- Berlin, Germany
-
15:44
(UTC +02:00) - http://www.joshdevins.com
- in/joshdevins
- @joshdevins
Stars
The highest-scoring AI memory system ever benchmarked. And it's free.
Curated list of AutoResearch use cases with optimization traces and open source implementations
Pal is a Personal Agent that Learns how you work by building a compounding knowledge base.
omo; the best agent harness - previously oh-my-opencode
Use Garry Tan's exact Claude Code setup: 23 opinionated tools that serve as CEO, Designer, Eng Manager, Release Manager, Doc Engineer, and QA
High-performance browser automation bridge and multi-instance orchestrator with advanced stealth injection and real-time dashboard.
AI agents running research on single-GPU nanochat training automatically
Beads, planning, and knowledge injection for AI coding agents
Beads - A memory upgrade for your coding agent
Supercharge Your LLM with the Fastest KV Cache Layer
⚡️A Blazing-Fast Python Library for Ranking Evaluation, Comparison, and Fusion 🐍
A high-throughput and memory-efficient inference and serving engine for LLMs
💨 Philips AirPurifier custom component for Home Assistant. Supports local CoAP protocol.
Run, manage, and scale AI workloads on any AI infrastructure. Use one system to access & manage all AI compute (Kubernetes, Slurm, 20+ clouds, on-prem).
A Python version of RankNet, LambdaRank and LambdaMart
A blazing fast inference solution for text embeddings models
📷 A Website created using Tailwind CSS, HTML, CSS and JavaScript that can be used as a Photographer Portfolio.
HTTP load testing tool and library. It's over 9000!
Create agents that monitor and act on your behalf. Your agents are standing by!
Backup each Discover Weekly to playlists
Notebooks & Example Apps for Search & AI Applications with Elasticsearch
Large Language Model Text Generation Inference
Extract datetimes and durations from natural language text as Python objects. Supports ranges, lists, and more.