GPT-5.2-Codex
GPT-5.2-Codex is OpenAI’s most advanced agentic coding model, built for complex, real-world software engineering and defensive cybersecurity work. It is a specialized version of GPT-5.2 optimized for long-horizon coding tasks such as large refactors, migrations, and feature development. The model maintains full context over extended sessions through native context compaction. GPT-5.2-Codex delivers state-of-the-art performance on benchmarks like SWE-Bench Pro and Terminal-Bench 2.0. It operates reliably across large repositories and native Windows environments. Stronger vision capabilities allow it to interpret screenshots, diagrams, and UI designs during development. GPT-5.2-Codex is designed to be a dependable partner for professional engineering workflows.
Learn more
DeepSeek Harness
DeepSeek Harness is an open source agent harness designed to keep AI agents working in real-world environments by helping them understand context, use tools, and continue operating across complex tasks. Built on the Cordis plugin system, every capability is a plugin that can be selected, swapped, extended, or recomposed through configuration without changing the core source code. Plugins provide models, tools, skills, sessions, sandboxes, storage, loops, scheduling, and the UI, while Cordis manages plugin mounting, dependencies, services, and events. Every run is traceable through an append-only session log that records system prompts, reasoning, tool calls and results, subagent scheduling, and context injections. The Trajectory view lets developers inspect these records by source, while resume, fork, search, and replay operate on the same event stream.
Learn more
Flue
Flue is an open agent framework for building durable AI agents with a programmable TypeScript harness. Created by the team behind Astro, it uses a React-like hooks API to compose agent behavior, persistent state, lifecycle events, models, tools, sandboxes, subagents, skills, and MCP servers in code. Agents are stateful and addressable over HTTP, keep context across conversations and events, and can change capabilities as work progresses. Flue records every session in a durable stream, so accepted work survives crashes, restarts, and deploys; interrupted sessions resume automatically and clients reconnect without starting over. Developers can run agents locally, in CI, from their own backend, or orchestrate them with systems such as Cloudflare Workflows and Inngest. Secure sandboxes let agents run commands, edit files, and do real work, while tools connect them to APIs and data. Flue is powered by Pi and supports different LLM providers, allowing teams to choose the models they want.
Learn more
OpenAI Agents API
The Agents API lets developers build and run cloud agents with the same harness and infrastructure that powers Codex, fully managed by OpenAI. A production-ready agent can be created with a single API call by specifying the task, model, tools, and environment, while OpenAI hosts and maintains the agent harness. Developers can choose where agents run: in an OpenAI-hosted sandbox, on their own infrastructure, or through supported sandbox partners. OpenAI-hosted sandboxes provide secure environments where agents can run code, work with files, use packages, skills, and plugins, and produce artifacts. The API is designed for long-running work, with automatic context compaction that preserves relevant information as sessions span multiple context windows. Tool search loads relevant tool definitions only when needed, while programmatic tool calling lets agents run calls in parallel, chain related operations, and filter or combine results in code.
Learn more