{"id":37943973,"url":"https://github.com/plaited/acp-harness","last_synced_at":"2026-01-21T15:08:13.663Z","repository":{"id":332845398,"uuid":"1135157745","full_name":"plaited/acp-harness","owner":"plaited","description":"CLI for agent evaluation. Capture trajectories, run trials with pass@k metrics, and score with polyglot graders (TypeScript, Python, any language).","archived":false,"fork":false,"pushed_at":"2026-01-18T09:03:21.000Z","size":272,"stargazers_count":0,"open_issues_count":1,"forks_count":0,"subscribers_count":0,"default_branch":"main","last_synced_at":"2026-01-18T16:58:54.647Z","etag":null,"topics":["acp","agent-client-protocol","agent-evaluation","ai-agents","bun","cli","eval-harness","grader","jsonl","llm-evaluation","pass-at-k","trajectory-capture","typescript"],"latest_commit_sha":null,"homepage":"","language":"TypeScript","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"isc","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/plaited.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":".github/CODEOWNERS","security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null,"notice":null,"maintainers":null,"copyright":null,"agents":null,"dco":null,"cla":null}},"created_at":"2026-01-15T18:07:11.000Z","updated_at":"2026-01-17T23:01:18.000Z","dependencies_parsed_at":null,"dependency_job_id":null,"html_url":"https://github.com/plaited/acp-harness","commit_stats":null,"previous_names":["plaited/acp-harness"],"tags_count":10,"template":false,"template_full_name":null,"purl":"pkg:github/plaited/acp-harness","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/plaited%2Facp-harness","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/plaited%2Facp-harness/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/plaited%2Facp-harness/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/plaited%2Facp-harness/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/plaited","download_url":"https://codeload.github.com/plaited/acp-harness/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/plaited%2Facp-harness/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":28635123,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-01-21T14:50:40.221Z","status":"ssl_error","status_checked_at":"2026-01-21T14:48:59.225Z","response_time":86,"last_error":"SSL_connect returned=1 errno=0 peeraddr=140.82.121.5:443 state=error: unexpected eof while reading","robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":false,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["acp","agent-client-protocol","agent-evaluation","ai-agents","bun","cli","eval-harness","grader","jsonl","llm-evaluation","pass-at-k","trajectory-capture","typescript"],"created_at":"2026-01-16T17:47:53.479Z","updated_at":"2026-01-21T15:08:13.639Z","avatar_url":"https://github.com/plaited.png","language":"TypeScript","funding_links":[],"categories":[],"sub_categories":[],"readme":"# @plaited/acp\n\n[![npm version](https://img.shields.io/npm/v/@plaited/acp.svg)](https://www.npmjs.com/package/@plaited/acp)\n[![CI](https://github.com/plaited/acp-harness/actions/workflows/ci.yml/badge.svg)](https://github.com/plaited/acp-harness/actions/workflows/ci.yml)\n[![License: ISC](https://img.shields.io/badge/License-ISC-blue.svg)](https://opensource.org/licenses/ISC)\n\nUnified ACP client and evaluation harness for TypeScript/Bun projects. Connect to ACP-compatible agents programmatically, capture full trajectories, and pipe to downstream analysis tools.\n\n## Installation\n\n```bash\nbun add @plaited/acp\n```\n\n**Prerequisite:** Install an ACP adapter:\n\n```bash\nnpm install -g @zed-industries/claude-code-acp\n```\n\n## Quick Start\n\n```typescript\nimport { createACPClient, createPrompt, summarizeResponse } from '@plaited/acp'\n\nconst client = createACPClient({\n  command: ['claude-code-acp'],\n  cwd: '/path/to/project',\n})\n\nawait client.connect()\nconst session = await client.createSession()\n\nconst { updates } = await client.promptSync(\n  session.id,\n  createPrompt('Create a function that validates email addresses')\n)\n\nconst summary = summarizeResponse(updates)\nconsole.log(summary.text, summary.completedToolCalls)\n\nawait client.disconnect()\n```\n\n## Recommended: Use the Bundled Plugin\n\nThis package includes a comprehensive **eval-harness plugin** designed for AI-assisted evaluation development. The plugin provides:\n\n- Complete API reference for `createACPClient` and helpers\n- Harness CLI usage with all options and examples\n- Output format schemas (summary and judge formats)\n- LLM-as-judge evaluation templates\n- Downstream integration patterns (Braintrust, jq, custom scorers)\n- Docker execution guidance\n\n### Install the Plugin\n\nInstall via the Plaited marketplace:\n\n**Claude Code:**\n\n```bash\n/plugin marketplace add plaited/marketplace\n```\n\n**Other AI coding agents:**\n\n```bash\ncurl -fsSL https://raw.githubusercontent.com/plaited/marketplace/main/install.sh | bash -s -- --agent \u003cagent-name\u003e --plugin acp-harness\n\nSupported agents: gemini, copilot, cursor, opencode, amp, goose, factory\n```\n\nOnce installed, the plugin auto-activates when working on evaluation tasks. Ask your AI agent to help you:\n\n- Set up evaluation prompts\n- Configure the harness CLI\n- Design scoring pipelines\n- Integrate with Braintrust or custom analysis tools\n\nThe plugin contains everything needed to build agent evaluations - use it as your primary reference.\n\n## Development\n\n```bash\nbun install          # Install dependencies\nbun run check        # Type check + lint + format\nbun test             # Run unit tests\nbun run check:write  # Auto-fix issues\n```\n\n## Requirements\n\n- **Runtime:** Bun \u003e= 1.2.9\n- **ACP Adapter:** `@zed-industries/claude-code-acp` or compatible\n- **API Key:** `ANTHROPIC_API_KEY` environment variable\n\n## License\n\nISC © [Plaited Labs](https://github.com/plaited)\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fplaited%2Facp-harness","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fplaited%2Facp-harness","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fplaited%2Facp-harness/lists"}