Initialize repository with benchmark template

.github/workflows/deploy.yml

@@ -0,0 +1,69 @@
+name: Deploy Next.js site to Pages
+
+on:
+  push:
+    branches: ["main"]
+  pull_request:
+    types: [opened, reopened, synchronize, closed]
+  workflow_dispatch:
+
+permissions:
+  contents: write
+  pull-requests: write
+  pages: write
+  id-token: write
+
+concurrency:
+  group: ${{ github.workflow }}-${{ github.head_ref || github.ref_name }}
+  cancel-in-progress: true
+
+jobs:
+  build-and-deploy:
+    runs-on: ubuntu-latest
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v4
+
+      - name: Install Node.js
+        uses: actions/setup-node@v4
+        with:
+          node-version: 22
+
+      - name: Setup Bun
+        uses: oven-sh/setup-bun@v2
+        with:
+          bun-version: latest
+
+      - name: Install dependencies
+        run: bun install --frozen-lockfile
+        working-directory: site
+
+      - name: Setup Pages
+        id: setup_pages
+        uses: actions/configure-pages@v5
+
+      - name: Set base uri
+        run: |
+          if [ "${{ github.event_name }}" = "pull_request" ]; then
+            echo "NEXT_PUBLIC_BASE_PATH=${{ steps.setup_pages.outputs.base_path }}/pr-preview/pr-${{ github.event.pull_request.number }}" >> "$GITHUB_ENV"
+          else
+            echo "NEXT_PUBLIC_BASE_PATH=${{ steps.setup_pages.outputs.base_path }}" >> "$GITHUB_ENV"
+          fi
+
+      - name: Build with Next.js
+        run: bun run build
+        working-directory: site
+
+      - name: Deploy preview
+        if: github.event_name == 'pull_request'
+        uses: rossjrw/pr-preview-action@v1
+        with:
+          source-dir: site/out
+
+      - name: Deploy production
+        if: github.event_name == 'push' && github.ref == 'refs/heads/main'
+        uses: JamesIves/github-pages-deploy-action@v4
+        with:
+          clean-exclude: pr-preview/
+          force: false
+          folder: site/out

.gitignore

@@ -0,0 +1,49 @@
+# See https://help.github.com/articles/ignoring-files/ for more about ignoring files.
+
+# dependencies
+node_modules
+.pnp
+.pnp.*
+.yarn/*
+!.yarn/patches
+!.yarn/plugins
+!.yarn/releases
+!.yarn/versions
+
+__pycache__/
+*.py[cod]
+*$py.class
+
+# testing
+coverage
+
+# next.js
+.next/
+
+# The `out` directory should not be ignored by version control
+out/
+
+# production
+build
+
+# misc
+.DS_Store
+*.pem
+*~
+\#*
+
+# debug
+npm-debug.log*
+yarn-debug.log*
+yarn-error.log*
+
+# local env files
+.env*.local
+.env*
+
+# vercel
+.vercel
+
+# typescript
+*.tsbuildinfo
+next-env.d.ts

.zealt/config.json

@@ -0,0 +1,5 @@
+{
+  "title": "Typesense Benchmark",
+  "description": "Performance results of AI coding models on Typesense tasks, measuring success rate and execution time with high precision.",
+  "github_repo": "https://github.com/kweizh/typesense-benchmark"
+}

README.md

@@ -1 +1,46 @@
-# typesense-benchmark
+
+# Typesense Benchmark
+
+This repository contains benchmarks for evaluating AI models on **Typesense**.
+
+You can view the evaluation reports at [https://kweizh.github.io/typesense-benchmark/](https://kweizh.github.io/typesense-benchmark/).
+
+## Project Structure
+
+- `tasks/`: Contains the benchmark tasks, each with its own instructions.
+- `jobs/`: Stores the results of benchmark runs.
+- `site/`: A Next.js application to visualize benchmark results.
+
+## Getting Started
+
+This benchmark is evaluated using the [Harbor framework](https://github.com/harbor-framework/harbor) and the [Pochi agent](https://github.com/TabbyML/pochi).
+
+### Running Evaluation
+
+You can run the evaluation using the Harbor CLI. Here is an example:
+
+```bash
+harbor run \
+  --agent codex \
+  --model "gpt-5.2-codex" \
+  --env daytona \
+  --path ./tasks \
+  --n-attempts 1 \
+  --max-retries 5 \
+  --n-concurrent 5 \
+  --retry-include RuntimeError \
+  --retry-include DaytonaError \
+  --retry-include AgentTimeoutError
+```
+
+### Evaluation Details
+
+Before starting the evaluation, you should set the necessary environment variables for your chosen agent.
+For example, if using Pochi, you should export `POCHI_API_KEY`.
+
+Evaluation can be run locally with Docker (default), or using [Daytona.io](https://www.daytona.io/) by setting `--env daytona`.
+
+When running with Daytona, please note that Daytona blocks some network access for tier 1 and tier 2 users. If you meet any network issues, please refer to [Daytona network limits](https://www.daytona.io/docs/en/network-limits/).
+
+---
+Generated by [Zealt](https://github.com/TabbyML/zealt)