LLaDA2.2-flash v2.2
LLaDA2.2-flash is an agent-oriented Mixture-of-Experts (MoE) diffusion language model designed for long-context agentic workloads. It introduces Levenshtein Editing with DELETE and INSERT control tokens to enable efficient parallel generation, error correction, and multi-turn tool use.
SIE (Superlinked Inference Engine) v0.7.1
SIE is an open-source, self-hosted inference server designed to run a wide variety of AI models for agentic workflows, including embedding, reranking, entity extraction, and text generation. It provides a unified API that replaces fragmented model-specific servers, allowing developers to serve over 100 models from a single cluster with on-demand loading.
Agent Orchestrator v0.12.1
Agent Orchestrator is an open-source development tool designed to manage fleets of AI coding agents in parallel. It provides a centralized dashboard to monitor agent sessions, handle git worktree isolation, and autonomously manage CI failures, code reviews, and merge conflicts.
Box v1.0
box is a persistent Linux (Ubuntu) virtual machine sandbox designed specifically for AI agents and agent factories. It provides full machine capabilities including SSH/SCP access, Docker support, and a 60fps virtual desktop, allowing agents to build, run, and ship software in isolated environments.
Macaron V1 Venti vV1-Venti
Macaron-V1-Venti is a 748B-parameter flagship AI model designed for personal intelligence, complex tool use, and coding workflows. It utilizes a Mixture of LoRA (MoL) architecture built on the GLM-5.2 base model, featuring specialized adapters for chat, agentic tasks, coding, and Generative UI.
Adapt-1 vPreview
Adapt-1 Preview is a non-transformer, neuro-symbolic substrate designed for test-time learning. It enables applications to learn and adapt while operating by maintaining a persistent, inspectable state without requiring task-specific pretraining or an LLM in the decision loop.
LFM2.5-2.6B v2.5
LFM2.5-2.6B is a compact, agentic foundation model designed for efficient on-device deployment. It features a 128K context window and is specifically optimized for agentic workflows, including planning, tool use, and multi-step task execution.
Xata
Xata is an open-source, cloud-native Postgres platform designed for Kubernetes that enables instant database branching using copy-on-write storage. It provides advanced features like scale-to-zero compute, high availability, and automated management, making it ideal for development environments and AI agent workloads.
Codex Security Review vResearch Preview
Codex Security Review is an AI-powered security analysis tool designed to perform in-depth evaluations of GitHub pull requests. It analyzes code diffs, repository context, and custom threat models to identify and report security vulnerabilities with high precision.
SDK Bridge v1.0.27
The Cursor SDK Bridge is an open-source protocol and local server that enables developers to drive Cursor agents from any programming language. By providing a stable sdk.v1 protobuf contract, it allows languages like Rust, Go, and Java to interact with Cursor's agent runtime without requiring direct dependency on the official TypeScript or Python SDKs.
Agent Plugins v1.0.0
Agent Plugins is an open, vendor-neutral standard for packaging reusable components into portable plugins for AI agents. It provides a consistent format for bundling Agent Skills and Model Context Protocol (MCP) servers, allowing them to be discovered and loaded across different compatible AI agent clients.
Kiro Crew v0.1.3
Kiro Crew is an open-source, persistent development workspace designed to transform AI coding agents into autonomous engineering teams. It enables agents to maintain context across sessions, schedule recurring tasks, and integrate with various developer tools for long-running workflows.