Search

Your AI agent pokes you when it's done — zero-config, one command: npx -y dxremote

Memory infrastructure for AI agents — citations, audit trails, BYO-LLM

Python SDK for the ObjectiveAI API.

Momoka - An personal AI assistant.

A local-first self-improvement kernel for agents. Turns traces into tested memory so agents improve without fine-tuning.

Granite 4.1 8B is a dense, decoder-only 8-billion-parameter language model from IBM, part of the Granite 4.1 family. It supports a 131K-token context window and is designed for enterprise tasks...

Owl Alpha is a high-performance foundation model designed for agentic workloads. Natively supports tool use, and long-context tasks, with strong performance in code generation, automated workflows, and complex instruction execution....

LangChain Agent - NEAR Content Creator

LangChain Agent - NEAR Data Analyst

LangChain Agent - NEAR NFT Collector

Claude Code skills for senior academics — turning knowledge work into daily practice.

OpenCode.ai implementation in Rust - High-performance AI coding agent with streaming LLM, tool execution, TUI, Web UI, MCP, LSP integrations

A Claude Code plugin that gives Claude a self-introspection tool for its own subscription quota — so it can warn you before a long task runs out of budget.

Saidkick is an IntelliJ plugin built at HackUPC that acts like a real coding buddy inside your IDE. It pays attention to how you work and steps in when you’re stuck, sending a quick nudge or asking if you need help. It has a customizable personality, so it feels less like a tool and more like someone keeping you on track while you code.

The Open Agent Tools Protocol (OATs) enables small function calling models (functiongemma-270m-it) to call tools from many open source repos using a compressed format

Artifact repository for the paper "MatchFixAgent: Language-Agnostic Autonomous Repository-Level Code Translation Validation and Repair", In Proceedings of The 43rd International Conference on Machine Learning (ICML 2026), Seoul, South Korea, July 2026

Board-mediated multi-agent coordination in ~500 lines of Python

KavachOS DAN gate + budget guard for CrewAI agents — pre-execution governance via AEGIS

KavachOS DAN gate callback for LangChain agents — pre-execution governance via AEGIS

Roomy — local-first LangChain agent context observability (import as `roomy`)