# OpenCode Projects at AI Tinkerers

> Canonical HTML: https://aitinkerers.org/technologies/opencode
> Markdown URL: https://aitinkerers.org/technologies/opencode.md
> Technology record last updated: 2026-02-22T16:48:56Z
> Generated: 2026-09-21T11:43:04Z

OpenCode is the open-source AI coding agent (CLI tool), integrating LLMs like GPT-5 and Claude Sonnet 4 directly into the terminal for fast, context-aware development.

OpenCode is the open-source AI coding agent, built for terminal-first developers who demand speed and privacy. It connects your local files, Git history, and a choice of LLMs (e.g., OpenAI's GPT-5 Nano, Anthropic's Claude Sonnet 4) to execute complex tasks directly from the command line . The tool bypasses IDE and browser dependencies, allowing developers to triage issues, fix errors, or implement features with commands like `opencode fix error in main.go` . With over 26,000 GitHub stars by October 2025, OpenCode delivers a secure, context-aware coding partner that keeps your code local and your workflow efficient .

- Official technology site: https://opencode.ai
- Public AI Tinkerers demos and talks: 12
- Result page: 1 of 1

## Recent Public Talks and Demos

### [Meet North Mini Code: Cohere's first model for developers.](https://montreal.aitinkerers.org/talks/rsvp_RFfBetDE0zk)

North Mini Code is a 30B parameter MoE coding model (3B active) that Cohere released June 9 under Apache 2.0, trained specifically for agentic software engineering. We will demo it live in OpenCode so you can watch it work through an agentic coding task end to end. Alongside the live agent session, we'll walk through the architecture and the post-training pipeline that got it there: two stages of SFT followed by async RLVR across terminal and SWE environments.

- Event context: AI Tinkerers Montreal - June Demo Meetup — 2026-06-17 — Montreal
- Public talk page: https://montreal.aitinkerers.org/talks/rsvp_RFfBetDE0zk

### [Is your skill still doing the right thing?](https://poland.aitinkerers.org/talks/rsvp_zcI9G1vqNok)

A new testing tool that lets you write tests to verify that your SKILL.md is followed by the most popular agents (Codex, Claude Code, OpenCode, and Cursor Agent) and that the workflow behaves exactly as expected, with assertions on loaded skills, files read, commands invoked, tokens used, and returned text.

- Event context: AI Tinkerers Poland #3 - Meetup in Wrocław — 2026-05-06 — Poland
- Public talk page: https://poland.aitinkerers.org/talks/rsvp_zcI9G1vqNok

### [Harness Engineering to Stop Waiting on AI and Defeat the "Dumb Zone"](https://st-louis.aitinkerers.org/talks/rsvp_n9X4ZKjuLLk)

We built a deterministic TypeScript harness that orchestrates multi-agent development pipelines, shifting our workflow from synchronously waiting on LLMs to managing them asynchronously. By simulating the PM and architect layer upfront, forcing strict context resets during implementation, and demanding empirical validation through browser automation, this harness effectively 3x'd our team's productivity.

- Event context: AI Tinkerers St. Louis: April 2026 Meetup — 2026-04-14 — St. Louis
- Public talk page: https://st-louis.aitinkerers.org/talks/rsvp_n9X4ZKjuLLk

### [From Abacus to AI: Small Potatoes, Big Results](https://hong-kong.aitinkerers.org/talks/rsvp_3XIaboEtPiM)

I'll share my real, month-long journey as a complete non-coder who used today's AI tools (like Grok, Copilot, Claude Haiku, and especially Claude Sonnet) to build actual working things: two World of Warcraft in-game addons for my uncles to track character stats and items automatically, a "Next Bus" app for our island's private bus routes (pulling schedules from PDFs and images), and a simple dinner-bell phone app that rings my phone when someone hits bell button their phone. The talk walks through the messy reality — starting with total confusion (SQL commas feeling like ancient abacus work, AWS looking like a blurry PS2 game, pasting code line-by-line and debugging parentheses I didn't understand), failing a lot, switching models when one got stuck, and eventually getting functional apps and addons. I'll show how I "failed faster" by iterating quickly, using my own low-tech version control (100+ numbered folders), and leaning on different AIs for different strengths. It's not about becoming a pro developer overnight — it's about an ordinary person getting useful results with zero prior experience.

- Event context: AI Tinkerers Hong Kong GBA at the Hive: Creative AI Demos & Technical Show-and-Tell — 2026-03-26 — Hong Kong
- Public talk page: https://hong-kong.aitinkerers.org/talks/rsvp_3XIaboEtPiM

### [How I code](https://orange-county.aitinkerers.org/talks/rsvp_eumtsm6BAjk)

I'll provide a succinct rundown of how I use agents to code, my environment, setup, and preferred coding agents.

- Event context: AI Tinkerers OC - March 11, 2026 Meetup — 2026-03-12 — Orange County
- Public talk page: https://orange-county.aitinkerers.org/talks/rsvp_eumtsm6BAjk

### [Claude Code in a Box - How to Actually Evaluate Coding Agents](https://berlin.aitinkerers.org/talks/rsvp_fB_XbaVcN1k)

Demo how to eval Claude Code vs itself (with different models/settings) or Codex/OpenCode on Production PRs using Harbor and deep insights into Agent Trajectories

- Event context: AI Tinkerers Berlin Meetup - March 11, 2026 — 2026-03-11 — Berlin
- Public talk page: https://berlin.aitinkerers.org/talks/rsvp_fB_XbaVcN1k

### [An engineering team in your pocket](https://ho-chi-minh-city.aitinkerers.org/talks/rsvp_U8eNYBDAmok)

CAR is a meta-harness on top of your favorite coding agent that allows you to have an engineering team in your pocket anywhere you go. Self host on a Mac mini or any linux machine, use your existing coding subscriptions, and work on multi-hour and multi-day builds. You do the planning the agents take care of the rest. https://github.com/Git-on-my-level/codex-autorunner

- Event context: AI Tinkerers Ho Chi Minh City: From Prompt to Agent — 2026-03-07 — Ho Chi Minh City
- Public talk page: https://ho-chi-minh-city.aitinkerers.org/talks/rsvp_U8eNYBDAmok

### [QuAI: The Vibe-Coded AI Writing Assistant I Use Every Day](https://montreal.aitinkerers.org/talks/rsvp_c6ieg8zqrj4)

I'll be presenting how I used vibe-coding to solve a personal challenge and showcasing my solution: QuAI, a desktop app I use daily for writing on my Mac. I will also discuss the tech stack and tools I utilized. Since it was vibe-coded, I don't even know all the details; however, because people are now asking for access, I'm considering moving toward agentic engineering, where I will actually deep-dive into the code and structure.

- Event context: AI Tinkerers Montreal - February 2026 Meetup — 2026-02-24 — Montreal
- Public talk page: https://montreal.aitinkerers.org/talks/rsvp_c6ieg8zqrj4

### ["Review Before Review" — the paradox of fixing code before it hits review](https://boston.aitinkerers.org/talks/rsvp_9tEaK6_3R68)

LLMs keep getting better with every release but code reliability is still an issue. Coding agents dont reliably enforce user defined guardrails and/or completely bypass instructions. (Wrote about it here - https://hasaber8.github.io/agents-and-me-experiments-with-ai-workflows-in-production/) After months of experimenting with AI workflows in production, I've found a way to make Claude actually follow the rules. ATX (Agent Nexus) seamlessly connects to ClaudeCode, and OpenCode provides real-time feedback, enforcing rules and standards before they ever reach code review.

- Event context: {Cancelled due to Blizzard Warning } AI Tinkerers Boston: February 2026 Meetup — 2026-02-23 — Boston
- Public talk page: https://boston.aitinkerers.org/talks/rsvp_9tEaK6_3R68

### [Securing Agent Swarms: Detection & Enforcement at the Tool Boundary (OpenClaw + Beyond)](https://nyc.aitinkerers.org/talks/rsvp_a6syk3sS0cc)

Agentic coding isn’t “one process on one host” anymore. It’s a swarm of local and hosted planners/coders/reviewers using tools that touch files, run commands, and egress to the internet. The security boundary isn’t the prompt; it’s the tool boundary where intent becomes action. In this session I’ll do a walkthrough of a practical “SDR” layer for OpenClaw-style workflows: - Policy enforcement on filesystem + command execution (path allow/deny, traversal hardening, safe defaults) - Network egress control (where requests can go, CONNECT/TLS sanity checks, blocking risky sequences) - Signed receipts / audit trails so you can replay, diff, and prove what actually happened during a run - A small demo of writing a policy and watching it block + record tool calls in real time

- Event context: 🦞Demo Night: OpenClaw ft Convex — 2026-02-17 — New York City
- Public talk page: https://nyc.aitinkerers.org/talks/rsvp_a6syk3sS0cc

### [Running OpenCode with local models on NVidia DGX Spark](https://seattle.aitinkerers.org/talks/rsvp_77nc0LyZBqE)

I'll run my OpenCode setup with multiple agents that will use LLMs from a locally hosted NVidia DGX Spark. I'll have the DGX Spark with me. - I'll show the GPU usage and other metrics as the models are doing their job to show how fast/slow this setup it - I'll also run some of the agents on OpenRouter and Anthropic hosted LLM's to show the difference in quality

- Event context: AI Tinkerers Seattle: January Meetup — 2026-01-31 — Seattle
- Public talk page: https://seattle.aitinkerers.org/talks/rsvp_77nc0LyZBqE

### [Coding agents and data science: building hill-climbing environments for LLMs](https://london.aitinkerers.org/talks/rsvp_3sAh2NjfCTQ)

In this project, I give dozens of coding agents access to an environment where they try to reverse engineer an algorithm created by Spotify that assigns a tasteful background color to an image of an album cover. Seemingly trivial, the correct solution requires a complex set of techniques, heuristics, and parameters. I let dozens of different models on different coding platforms loose on the task and have some interesting findings. The environment includes some 'training' data and the model's task is to code up a good solution. The agent has access to a set of scripts to run predictions, analyze results, and view failing samples individually. As a task, it tests an agent's ability to ideate and analyze results over a long conversation. The purpose of the talk is not just to show off this particular project, but to showcase how proper environment setup and 'data science thinking' can enable coding agents to hill-climb towards better solutions faster. These ideas are relevant far beyond clearly defined X -> Y tasks. I use similar techniques regularly when building and benchmarking agentic systems. Rough demo plan: - Intro to the task, set off a coding agent live to come up with a solution. - Walk through the environment, show off some interesting results and analysis of previous runs. - Talk about the general idea of building hill-climbing environments for LLMs.

- Event context: AI Tinkerers London Meetup - 25th November 2025 — 2025-11-25 — London
- Public talk page: https://london.aitinkerers.org/talks/rsvp_3sAh2NjfCTQ

## Related Technologies

- [Claude Code](https://aitinkerers.org/technologies/claude-code) ([Markdown](https://aitinkerers.org/technologies/claude-code.md)) — 215 public demos
- [Codex](https://aitinkerers.org/technologies/codex) ([Markdown](https://aitinkerers.org/technologies/codex.md)) — 44 public demos
- [TypeScript](https://aitinkerers.org/technologies/typescript) ([Markdown](https://aitinkerers.org/technologies/typescript.md)) — 205 public demos
- [Harbor](https://aitinkerers.org/technologies/harbor) ([Markdown](https://aitinkerers.org/technologies/harbor.md)) — 2 public demos
- [Agent harness](https://aitinkerers.org/technologies/agent-harness) ([Markdown](https://aitinkerers.org/technologies/agent-harness.md)) — 1 public demo
- [Agent Nexus](https://aitinkerers.org/technologies/agent-nexus) ([Markdown](https://aitinkerers.org/technologies/agent-nexus.md)) — 1 public demo
- [AWS](https://aitinkerers.org/technologies/aws) ([Markdown](https://aitinkerers.org/technologies/aws.md)) — 38 public demos
- [Claude](https://aitinkerers.org/technologies/claude) ([Markdown](https://aitinkerers.org/technologies/claude.md)) — 173 public demos
- [Claude CLI](https://aitinkerers.org/technologies/claude-cli) ([Markdown](https://aitinkerers.org/technologies/claude-cli.md)) — 3 public demos
- [Claude CLI/SDK](https://aitinkerers.org/technologies/claude-cli-sdk) ([Markdown](https://aitinkerers.org/technologies/claude-cli-sdk.md)) — 1 public demo
- [Claude Haiku](https://aitinkerers.org/technologies/claude-haiku) ([Markdown](https://aitinkerers.org/technologies/claude-haiku.md)) — 10 public demos
- [Claude SDK](https://aitinkerers.org/technologies/claude-sdk) ([Markdown](https://aitinkerers.org/technologies/claude-sdk.md)) — 4 public demos
- [Claude Sonnet](https://aitinkerers.org/technologies/claude-sonnet) ([Markdown](https://aitinkerers.org/technologies/claude-sonnet.md)) — 20 public demos
- [Cursor](https://aitinkerers.org/technologies/cursor) ([Markdown](https://aitinkerers.org/technologies/cursor.md)) — 65 public demos
- [Cursor Agent](https://aitinkerers.org/technologies/cursor-agent) ([Markdown](https://aitinkerers.org/technologies/cursor-agent.md)) — 1 public demo
- [Dart](https://aitinkerers.org/technologies/dart) ([Markdown](https://aitinkerers.org/technologies/dart.md)) — 3 public demos
- [Elluminate](https://aitinkerers.org/technologies/elluminate) ([Markdown](https://aitinkerers.org/technologies/elluminate.md)) — 4 public demos
- [Flash](https://aitinkerers.org/technologies/flash) ([Markdown](https://aitinkerers.org/technologies/flash.md)) — 14 public demos