# Agent harness Projects at AI Tinkerers

> Canonical HTML: https://aitinkerers.org/technologies/agent-harness
> Markdown URL: https://aitinkerers.org/technologies/agent-harness.md
> Technology record last updated: 2026-05-26T18:05:39Z
> Generated: 2026-08-24T21:49:40Z

An agent harness is the operational infrastructure wrapping a raw language model to manage tool execution, state, and sandboxed environments, turning static text generation into an autonomous work engine.

While raw language models excel at text generation, they cannot natively execute code, manage persistent state, or call external APIs. The agent harness bridges this gap by serving as the execution layer that orchestrates system prompts, manages tool registries (like the Model Context Protocol), and runs isolated sandboxes. By handling the execution loops and error recovery that models cannot manage alone, a well-engineered harness can dramatically swing benchmark performance (such as LangChain's 13.7-point jump on Terminal-Bench 2.0) without changing the underlying model. This infrastructure layer is what ultimately transforms a static LLM into a reliable, production-ready autonomous agent.

- Official technology site: https://langchain-ai.github.io/posts/anatomy-of-an-agent-harness/
- Public AI Tinkerers demos and talks: 1
- 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

## Related Technologies

- [Harbor for containerized agent environments](https://aitinkerers.org/technologies/harbor-for-containerized-agent-environments) ([Markdown](https://aitinkerers.org/technologies/harbor-for-containerized-agent-environments.md)) — 1 public demo
- [Hugging Face](https://aitinkerers.org/technologies/hugging-face) ([Markdown](https://aitinkerers.org/technologies/hugging-face.md)) — 41 public demos
- [Live Demo](https://aitinkerers.org/technologies/live-demo) ([Markdown](https://aitinkerers.org/technologies/live-demo.md)) — 1 public demo
- [MoE](https://aitinkerers.org/technologies/moe) ([Markdown](https://aitinkerers.org/technologies/moe.md)) — 1 public demo
- [North Mini Code](https://aitinkerers.org/technologies/north-mini-code) ([Markdown](https://aitinkerers.org/technologies/north-mini-code.md)) — 1 public demo
- [North Mini Code (30B MoE, 3B active)](https://aitinkerers.org/technologies/north-mini-code-30b-moe-3b-active) ([Markdown](https://aitinkerers.org/technologies/north-mini-code-30b-moe-3b-active.md)) — 1 public demo
- [OpenCode](https://aitinkerers.org/technologies/opencode) ([Markdown](https://aitinkerers.org/technologies/opencode.md)) — 12 public demos
- [SWE-Agent and mini-SWE-agent harnesses for training and eval](https://aitinkerers.org/technologies/swe-agent-and-mini-swe-agent-harnesses-for-training-and-eval) ([Markdown](https://aitinkerers.org/technologies/swe-agent-and-mini-swe-agent-harnesses-for-training-and-eval.md)) — 1 public demo
- [SWE-Bench Verified and Terminal-Bench v2 for benchmarking](https://aitinkerers.org/technologies/swe-bench-verified-and-terminal-bench-v2-for-benchmarking) ([Markdown](https://aitinkerers.org/technologies/swe-bench-verified-and-terminal-bench-v2-for-benchmarking.md)) — 1 public demo
- [vLLM](https://aitinkerers.org/technologies/vllm) ([Markdown](https://aitinkerers.org/technologies/vllm.md)) — 33 public demos
- [vLLM for serving rollouts during async RL](https://aitinkerers.org/technologies/vllm-for-serving-rollouts-during-async-rl) ([Markdown](https://aitinkerers.org/technologies/vllm-for-serving-rollouts-during-async-rl.md)) — 1 public demo