OpenCode Integrations

nono is an open source, kernel-enforced sandbox for AI coding agents and LLM workloads. Unlike policy-based guardrails that intercept and filter operations, nono uses OS security primitives — Landlock on Linux and Seatbelt on macOS — to make unauthorised operations structurally impossible at the syscall level. Wrap any AI agent — Claude Code, OpenCode, OpenClaw, or any CLI process — with a single command. nono applies default-deny filesystem access, blocks destructive commands (rm, dd, chmod, sudo), isolates credentials and API keys, and cascades all restrictions to child processes. No escape mechanism exists once restrictions are applied. Built-in profiles get you running in seconds. Secrets inject securely from the system keystore and are zeroised on exit. Audit logging, atomic rollbacks, and Sigstore-attested policy signing are on the roadmap. Apache 2.0. From the creator of Sigstore.

Gemini 3.1 Flash-Lite is Google’s fastest and most cost-efficient model in the Gemini 3 series, designed for high-volume developer workloads. It delivers strong performance at scale while maintaining affordability, with pricing set at $0.25 per million input tokens and $1.50 per million output tokens. The model significantly improves speed, offering a 2.5x faster time to first answer token and a 45% increase in output speed compared to Gemini 2.5 Flash. Despite its lower cost tier, it achieves high benchmark results, including an Elo score of 1432 and strong performance across reasoning and multimodal evaluations. Gemini 3.1 Flash-Lite supports adaptive “thinking levels,” allowing developers to control how much reasoning power is used for different tasks. It is suitable for large-scale applications such as translation, content moderation, user interface generation, and simulation building.

GPT-5.3 Instant is an updated version of ChatGPT’s most-used model, designed to make everyday conversations more fluid, helpful, and accurate. The release focuses on improving tone, relevance, and conversational flow based directly on user feedback. It reduces unnecessary refusals and cuts back on overly cautious disclaimers, delivering clearer and more direct answers when appropriate. The model also improves how it integrates web results, providing better-contextualized information rather than long lists of loosely connected links. Accuracy has been strengthened, with measurable reductions in hallucinations across both high-stakes domains and everyday queries. GPT-5.3 Instant enhances creative writing capabilities, producing more textured, emotionally resonant prose. It is available to all ChatGPT users and developers via the API under ‘gpt-5.3-chat-latest,’ with legacy versions scheduled for retirement.

GPT-5.4 Pro is an advanced AI model developed by OpenAI to deliver high-performance capabilities for professional and complex tasks. It combines improvements in reasoning, coding, and agent-based workflows into a single unified system. The model is designed to work efficiently across professional tools such as spreadsheets, presentations, documents, and development environments. GPT-5.4 Pro also includes native computer-use capabilities, enabling AI agents to interact with software, websites, and operating systems to complete tasks. With support for up to one million tokens of context, it can manage long workflows and large datasets more effectively than previous models. The model also improves tool usage, allowing it to search for and select the right tools during multi-step processes. By delivering more accurate outputs with fewer tokens, GPT-5.4 Pro helps professionals complete complex work faster and more efficiently.

GPT-5.4 Thinking is an advanced reasoning-focused AI model available within ChatGPT, designed to help users complete complex professional tasks more effectively. It combines improvements in reasoning, coding, and agent-based workflows to provide more accurate and reliable outputs. The model can present an upfront outline of its reasoning process, allowing users to adjust instructions while it is generating a response. This capability helps produce results that better align with user goals without requiring multiple follow-up prompts. GPT-5.4 Thinking also improves deep web research, enabling it to locate and synthesize information from multiple sources more efficiently. With stronger context management, it can handle longer conversations and complex problem-solving tasks with greater coherence. These capabilities make GPT-5.4 Thinking well suited for professional knowledge work and advanced analytical tasks.

GPT-5.4 mini is a fast and efficient AI model designed for high-performance tasks such as coding, reasoning, and multimodal understanding. It delivers strong capabilities similar to larger models while maintaining lower latency and cost. The model is optimized for responsive applications where speed is critical, including coding assistants and real-time workflows. GPT-5.4 mini supports advanced features such as tool use, function calling, and image interpretation. It performs well on complex tasks while running significantly faster than previous mini models. The model is also suitable for subagent systems, where it handles smaller tasks within larger AI workflows. By combining speed, efficiency, and strong performance, GPT-5.4 mini enables scalable AI applications across various use cases.

GPT-5.4 nano is a lightweight and highly efficient AI model designed for fast, cost-effective task execution. It is optimized for simple and high-volume tasks such as classification, data extraction, and basic coding support. The model delivers quick responses with minimal latency, making it ideal for real-time and large-scale applications. GPT-5.4 nano improves significantly over previous nano models in both performance and efficiency. It supports essential capabilities like tool use and structured data processing. The model is commonly used as a supporting component within larger AI systems. By focusing on speed and affordability, GPT-5.4 nano enables scalable automation across various workflows.

Xiaomi MiMo-V2.5-Pro is an advanced open-source AI model designed to handle complex, long-horizon tasks with strong agentic capabilities. It features a Mixture-of-Experts architecture with over one trillion parameters and a large context window of up to one million tokens. The model is built to perform sophisticated reasoning, coding, and problem-solving across extended workflows. It demonstrates high performance on benchmark tests related to software engineering, reasoning, and general intelligence. MiMo-V2.5-Pro can autonomously complete complex projects, such as building full software systems or optimizing engineering designs. It uses hybrid attention mechanisms to balance efficiency and performance across long contexts. The model is also optimized for token efficiency, reducing computational cost while maintaining strong results. By combining scalability, efficiency, and advanced reasoning, MiMo-V2.5-Pro represents a major step forward in open-source AI models.

Xiaomi MiMo-V2.5 is an advanced open-source AI model designed to combine strong agentic capabilities with native multimodal understanding. It can process and reason across text, images, and audio within a single unified system. The model uses a sparse Mixture-of-Experts architecture with hundreds of billions of parameters for efficient performance. It supports an extended context window of up to one million tokens, enabling long and complex workflows. MiMo-V2.5 is built to handle tasks such as coding, reasoning, and multimodal analysis with high accuracy. It incorporates dedicated visual and audio encoders to enhance perception and cross-modal reasoning. The model demonstrates strong benchmark performance across coding, reasoning, and multimodal tasks. By combining multimodality, efficiency, and agentic intelligence, MiMo-V2.5 advances the capabilities of open-source AI systems.

Puter.js is the backend for AI-generated apps. Use your existing AI coding tool to build production-ready apps with up to 90% fewer AI tokens. Auth, cloud storage, database, OpenAI, Claude, Gemini, Grok, Kimi, DeepSeek, and more, all through a single JavaScript library. No API keys. Zero setup.

North Mini Code is Cohere’s first agentic coding model for developers and the inaugural member of its next generation of powerful models. Small, efficient, and open-source, it is built for the sovereign developer ecosystem and designed to deliver strong software development performance without requiring extensive hardware. North Mini Code is a mixture-of-experts model with 30B total parameters and 3B active parameters, giving developers access to agentic coding capabilities in a compact and efficient form. The model is optimized for code generation, agentic software engineering, and terminal tasks, with a 256K total context length and up to 64K maximum generation. It is built for real-world developer workflows, including understanding and orchestrating sub-agents, mapping system architecture, running code reviews, and supporting coding agents that need to reason through complex software tasks.

Constellation Gate AI is a drop-in defense layer for AI agents, built to sit between the agent and the model while screening every request for attacks and leaks. Gate acts as an inline gateway for coding agents and model APIs, protecting workflows without requiring major code changes. Users can point existing tools such as Claude Code, Cursor, OpenClaw, Codex, or OpenCode at Gate and inherit prompt-injection defense, secret scanning, PII redaction, token optimization, and a verifiable audit trail. The platform is designed around three real risks: prompt injection, credential and PII leakage, and hijacked tool calls. Instead of relying on the model to defend itself, Gate blocks attacks before they reach the model, redacts secrets before responses return, and stops attacker-controlled tool outputs before an agent acts on them. Gate accepts the same calls an agent already makes, forwards them to the model, scans every call and response in both directions.

HQ is the shared AI context layer for teams, giving the whole team and every AI tool one workspace to work from, with knowledge, skills, and workflows compounding in one place, and any agent running on top. It works as an operating system for AI workers over Claude Code, Cursor, Codex, ChatGPT, and Claude chat through MCP, so every teammate and every agent can start from the same shared context instead of separate chat histories, scattered files, and siloed workflows. HQ turns one person’s best work into team infrastructure: any prompt or workflow can become a reusable /command, then /hq-sync ships it to the whole team so anyone can run it in one step. Knowledge that usually lives across decisions, docs, playbooks, policies, projects, code, and ideas accumulates in HQ as the team works, creating one source of truth that every agent can search, reuse, and build on. Agents can be deployed into email and Slack, acting on top of the team’s skills and knowledge with full context.

Big Pickle is an AI model available through OpenCode Zen, a curated model provider focused on coding-agent workflows. The model is designed for text-based input, reasoning tasks, function calling, and developer workflows that require long-context understanding. Big Pickle supports a large context window, making it useful for working across bigger codebases, project files, technical prompts, and multi-step coding tasks. It can be accessed through OpenCode Zen using an OpenAI-compatible API format, allowing developers to integrate it into agentic coding tools and automation workflows. The model is positioned as a free or low-cost option within OpenCode’s coding-agent ecosystem. Big Pickle helps developers experiment with AI-assisted coding, reasoning, tool use, and long-context automation without relying only on premium frontier models.

Concentrate AI is the LLM gateway for fast-growing teams, one API for every major LLM provider, with routing, spend, logs, and controls in one place. It helps teams securely access, use, and manage AI through a single API, so every request can find the smarter, faster, cheaper model for the workflow or task. Teams can access 130+ models, benchmark speed, quality, and cost, and route each workload to the best fit without wiring separate provider APIs into every environment. Support bots, coding agents, internal tools, chat, and batch jobs do not need the same model or the same route, so Concentrate lets teams pick a model slug, limit allowed providers, sort by live latency, use fallbacks, and reroute traffic when a provider slows down, errors, or hits a rate limit. It also gives engineering, finance, security, and leadership a shared view of AI usage with request-level logs, models, provider, duration, token counts, spend, error rates, alerts, and exports.

condense.chat is an LLM input compression API and drop-in proxy that shrinks prompts, retrieved documents, tool outputs, and repeated agent context before they hit upstream models. Less context, same Claude Code; its harness intercepts an agent’s growing session history and passes it through compression models before it reaches the main model, helping long-running coding agents start each next turn with fewer tokens. Condense sits between an app and the upstream LLM provider, tracks the conversation as a content-addressed chain, and transparently compresses repeated context on the way upstream. Developers can point their SDK at the Condense provider route, add a Condense key, keep their existing provider key, and change nothing else. It supports Anthropic and OpenAI-compatible routes, plus pass-through behavior for other provider paths such as model lists and embeddings.

Laguna XS 2.1 is an upgraded open weight agentic coding model designed for long-horizon work on a local machine. It uses a 33-billion-parameter Mixture-of-Experts architecture with 3 billion activated parameters per token, retaining the same efficient architecture as Laguna XS.2 while improving multilingual software engineering and terminal-style task performance. The model is built to support coding agents that inspect repositories, reason through complex changes, use tools, execute commands, and continue working across extended tasks. It is served with a 256K context window, giving agents room to work with large codebases, lengthy histories, and multi-step workflows. Laguna XS 2.1 is supported by vLLM, SGLang, NVIDIA TensorRT-LLM, Hugging Face Transformers, and Ollama, with native llama.cpp support planned. It is available in BF16, FP8, INT4, and NVFP4 checkpoints, allowing developers to choose between maximum fidelity and configurations suited to tighter VRAM or compute budgets.

GPT-5.4 is an advanced artificial intelligence model developed by OpenAI to support complex professional and technical work. The model combines improvements in reasoning, coding, and agent-based workflows into a single system designed for real-world productivity tasks. GPT-5.4 can generate, analyze, and edit documents, spreadsheets, presentations, and other work outputs with greater accuracy and efficiency. It also features improved tool integration, enabling the model to interact with software environments and external tools to complete multi-step workflows. With enhanced context capabilities supporting up to one million tokens, GPT-5.4 can process and reason over very large amounts of information. The model also improves factual accuracy and reduces errors compared to earlier versions. By combining strong reasoning, coding ability, and tool use, GPT-5.4 helps users complete complex tasks faster and with fewer iterations.