ToolAI CodingDev ToolsOpen Sourceagentsclillm
OpenCode
Open-source AI coding agent from Anomaly (formerly SST) that runs in the terminal, as a desktop app, or as an IDE extension, and works with 75+ LLM providers including local models.
Added October 16, 2026
Install it with:
bash
curl -fsSL https://opencode.ai/v2/install | bashAlso on npm (@opencode/cli), Homebrew, Scoop, Chocolatey, AUR, mise and Nix. Out of the box you get a build agent with full access, a read-only plan agent you switch to with Tab, and a general subagent for multi-step searches. It loads the right language server for the project, runs several sessions in parallel, and turns a session into a share link. /init writes an AGENTS.md for the repo.
Providers come from Models.dev, the same team's model database. You can log in with an existing GitHub Copilot or ChatGPT Plus/Pro account, or use OpenCode Zen, their tested list of models. MIT licensed, over 200k stars on anomalyco/opencode, and the site says more than 16M developers use it every month.
Related
- Pi DurableDurable harness for long-running agents from the team behind the Pi coding agent. It checkpoints every step so a run survives crashes and evictions, and it now runs inside a Cloudflare Durable Object through the Agents SDK's PiHarness.
- e2eTesterArmy's open-source TypeScript test runner for web and mobile apps, where each test can be fully deterministic, fully agent-driven from natural-language goals, or a mix of both.
- Agent Skills Discovery RFCCloudflare's draft spec for publishing Agent Skills at a predictable URL — an index at /.well-known/agent-skills/ lists each skill as a single artifact with a type, a URL and a SHA-256 digest. Apache-2.0, v0.2.0, and a draft rather than a ratified IETF RFC.
- PostHog MCP AnalyticsAnalytics for MCP servers — every tool call an agent makes lands as a normal PostHog event, so you get per-tool failure and latency, the agent's own account of what it was after, and the tools it went looking for and didn't find. Beta, behind a feature preview.