Lite-Harness – Self-Hosted Cursor Agents (Use Claude Code/OpenCode)
We built this library because agent harnesses were too fragmented and we needed a simple abstraction to call multiple coding-agent SDKs. lite-harness has one function - query() import { query } from "@lite-harness/sdk"; for await (const message of query({ prompt: "Fix the failing test", options: { // swap harness between: "claude-agent", "openai-agents", "pi-ai" harness: "openai-agents", model: "gpt-5.5", }, })) { console.log(message); }
Lite-Harness – Self-Hosted Cursor Agents (Use Claude Code/OpenCode) launched on May 30, 2026 with 6 votes, #1,742 of 20,538 launches that month and more than 75% of that year's launches.
What it does
Unified API for running OpenCode, Claude Code, Codex agents - LiteLLM-Labs/lite-harness
Preview: the SDK is not published to npm or PyPI yet. Clone this repo to try it. If you want a packaged release, please file an issue . git clone https://github.com/LiteLLM-Labs/lite-harness.git cd lite-harness # install the backend server's deps once — the SDK auto-spawns it from the clone npm install --prefix src/sdk/server # pick a model — set the key for your provider: export ANTHROPIC_API_KEY=sk-ant-... # for harness "claude-code" export OPENAI_API_KEY=sk-... # for harness "codex" TypeScript Usage npm install --prefix src/sdk/typescript && npm run build --prefix src/sdk/typescript import { query } from "@lite-harness/sdk" ; const prompt = "Fix the failing test" ; // Claude Code harness…from github.com
In the maker’s words, at launch
We built this Dockerfile because we wanted a simple harness server to run our agents and get memory, durable sessions, cron scheduling, and a vault, out of the box.
Does a similar job
all alternatives →
HarnessRouter Community EditionAug 2026 · harnessrouter.ai · ▲397Open-source unified interface for agent harnesses
Harness by Autonomous6d ago · autonomous.ai · ▲288Every coding agent, every machine, one command center.
1CodeJan 2026 · github.com · ▲569Just to clarify the background a bit. This project wasn’t planned as a big standalone release at first. On January 16, Ollama added support for an Anthropic-compatible API, and I was curious how far this could be pushed in practice. I decided to try plugging local Ollama models directly into a Claude Code-style workflow and see if it would actually work end to end. Here is the release note from Ollama that made this possible: https://ollama.com/blog/claude Technically, what I do is pretty straightforward: - Detect which local models are available in Ollama. - When…
AgentAPI – HTTP API for Claude Code, Goose, Aider, and Codex2025 · github.com · ▲163HTTP API for Claude Code, Goose, Aider, Gemini, Amp, and Codex - coder/agentapi
Gambit, an open-source agent harness for building reliable AI agentsJan 2026 · github.com · ▲91Hey HN! Wanted to show our open source agent harness called Gambit. If you’re not familiar, agent harnesses are sort of like an operating system for an agent... they handle tool calling, planning, context window management, and don’t require as much developer orchestration. Normally you might see an agent orchestration framework pipeline like: compute -> compute -> compute -> LLM -> compute -> compute -> LLM we invert this so with an agent harness, it’s more like: LLM -> LLM -> LLM -> compute -> LLM -> LLM -> compute -> LLM Essentially you describe each agent in either a self contained…
More ai this month
the category →
Paintings by AI models: programs run through a simulation of oil paint.
AI · 20d ago · stillwet.art
PixVerse R2▲381A real-time world model you can explore and change
AI · 28d ago · world.pixverse.video
Source: Show HN post ↗ · launch text quoted in part
Launched alongside, May 2026
the whole month →
Parallel agents, diff reviewer, and multi-model comparisons
Dev tools · May 2026 · kilo.ai
Hey HN, Henry here from Cactus. We open-sourced Needle, a 26M parameter function-calling (tool use) model. It runs at 6000 tok/s prefill and 1200 tok/s decode on consumer devices. We were always frustrated by the little effort made towards building agentic models that run on budget phones, so we conducted investigations that led to an observation: agentic experiences are built upon tool calling, and massive models are overkill for it. Tool calling is fundamentally retrieval-and-assembly (match query to tool name, extract argument values, emit JSON), not reasoning. Cross-attention…
Life & fun · May 2026 · github.com
🌱 Private, quiet space for thinking. Simple app for .md files. - zakirullin/files.md
Dev tools · May 2026 · github.com