Cainew

The public gallery of animated pet for Codex, Claude Code, OpenCode y Gemini CLI

ESP32 desk dashboard that shows Claude Code usage

ktx is an executable context layer for data and analytics agents 🐙 Allow Claude Code, Codex, and any AI agent to query data accurately through MCP with skills, memory and a semantic layer

ADHD — a skill for coding agents. Tree-of-thought with pruning, built on the Claude & Codex Agent SDK. Fans out parallel divergent thoughts under different cognitive frames, scores, prunes traps, deepens the survivors. The no-brainer skill for creative and interdisciplinary work.

Agent memory for LLMs: 30 runnable Jupyter notebooks covering conversation buffers, vector stores, knowledge graphs, episodic and semantic memory, MemGPT, Mem0, Letta, Zep, Graphiti, LoCoMo benchmarks, and production patterns.

Tiny-vLLM is a high-performance LLM inference engine written in C++ and CUDA that aims to provide efficient language model execution. The project represents efforts to optimize AI model deployment with lean, performant implementations.

Multi-agent exploratory data analysis system with autonomous insights, visualization, preprocessing, and reporting workflows.

AI-driven inverse antenna design with real NEC2 + openEMS in the loop. Try the live in-browser playground.

Most AI agents forget you the moment the tab closes. Constellation Engine gives them a hippocampus — a living star map with spreading activation, Hebbian writeback, episodic recall, and post-turn consolidation. Local-first, model-agnostic, AGPL.

Create agents that monitor airspace activity 24/7 - military aircraft in a region, private or government jets, a GPS-jamming spike, or a travelling friend or family member - and get alerts the moment something relevant happens. Or just ask anything about what's flying right now. Powered by our own independent network of 5,600+ antennas across 120 countries. No code, no data engineering, no terabytes to store.

Most monitors just send an HTTP ping. But a 200 OK is useless if the JSON-RPC handshake fails. Our tool is different because it performs a true protocol-level check, acting exactly like a real AI client. Key features: Full Handshake: Executes the spec-defined initialize, ping, and tools/list sequence. Deep Visibility: Inspect exact JSON-RPC payloads and negotiated versions. Smart Auth: Parses RFC 9728 headers on 401s to surface exact token requirements.

An Apache 2.0 open-weight Flash model for real-world agents. Step 3.7 Flash combines vision, coding, search, tool use, 256K context, ~11B active params, and up to 400 TPS.

Rsync version 3.4.3 includes hundreds of commits from Claude, Anthropic's AI assistant, contributing significantly to the file synchronization tool's development. This represents a major collaboration between open-source software and AI-assisted coding.

Anthropic has surpassed OpenAI to become the most valuable AI startup, marking a significant shift in the competitive landscape of artificial intelligence companies. This milestone reflects growing investor confidence in Anthropic's approach to AI development and safety.

Shift, a robotics startup, is offering to clean homes for free as a way to generate training data for their future cleaning robots. This innovative approach uses real-world service to advance their autonomous home cleaning technology.

OpenRouter, an AI routing platform, has successfully raised $113 million in Series B funding to expand its infrastructure and services. The funding round demonstrates strong investor confidence in the company's model of providing unified access to multiple AI models.

As AI computing costs continue to surge, corporations are beginning to implement cost control measures and rationing strategies for their AI usage. The trend reflects growing concerns about the financial sustainability of widespread AI deployment in enterprise environments.

The status and future viability of MCP (Model Context Protocol) is being questioned, with discussions around whether the protocol has failed to meet its intended objectives. The title suggests uncertainty about the protocol's continued relevance in the AI ecosystem.