{"id":40068318,"url":"https://github.com/skitsanos/tiny-crew","last_synced_at":"2026-02-01T17:04:26.992Z","repository":{"id":280138096,"uuid":"867024970","full_name":"skitsanos/tiny-crew","owner":"skitsanos","description":"Multi-Agent AI system to tackle complex tasks through intelligent collaboration","archived":false,"fork":false,"pushed_at":"2026-01-19T07:59:33.000Z","size":177,"stargazers_count":5,"open_issues_count":1,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2026-01-19T14:16:55.202Z","etag":null,"topics":["ai","artificial-intelligence","crew","crewai","llm","llms","multi-agent","multi-agent-system","multi-agent-systems"],"latest_commit_sha":null,"homepage":"https://gedankrayze.com","language":"TypeScript","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/skitsanos.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"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":"2024-10-03T10:12:38.000Z","updated_at":"2026-01-19T07:59:37.000Z","dependencies_parsed_at":"2025-09-09T06:17:19.642Z","dependency_job_id":"52e2d934-a4cd-4677-a59c-23607d1a1c92","html_url":"https://github.com/skitsanos/tiny-crew","commit_stats":null,"previous_names":["skitsanos/tiny-crew"],"tags_count":5,"template":false,"template_full_name":null,"purl":"pkg:github/skitsanos/tiny-crew","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/skitsanos%2Ftiny-crew","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/skitsanos%2Ftiny-crew/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/skitsanos%2Ftiny-crew/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/skitsanos%2Ftiny-crew/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/skitsanos","download_url":"https://codeload.github.com/skitsanos/tiny-crew/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/skitsanos%2Ftiny-crew/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":28983432,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-02-01T16:29:42.054Z","status":"ssl_error","status_checked_at":"2026-02-01T16:29:41.428Z","response_time":56,"last_error":"SSL_read: 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":["ai","artificial-intelligence","crew","crewai","llm","llms","multi-agent","multi-agent-system","multi-agent-systems"],"created_at":"2026-01-19T08:04:13.806Z","updated_at":"2026-02-01T17:04:26.981Z","avatar_url":"https://github.com/skitsanos.png","language":"TypeScript","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Tiny Crew\n\nTinyCrew is a TypeScript framework that orchestrates multiple AI agents to solve complex tasks collaboratively.\n\n## Features\n\n- **Multi-Agent Orchestration** - Specialized agents with distinct goals working together\n- **Shared Memory** - Knowledge transfer and persistence between agents\n- **Tool Integration** - Extensible system using OpenAI Responses API\n- **Structured Output** - Type-safe JSON responses with Zod schema validation\n- **Conversation Management** - Multi-turn history with automatic summarization\n- **Response Streaming** - Real-time response delivery\n- **Agent Messaging** - Direct agent-to-agent communication\n- **Multi-Model Routing** - Cost optimization with purpose-based model selection\n- **Event System** - Comprehensive monitoring and hooks\n\n## Quick Start\n\n### Installation\n\n```bash\ngit clone https://github.com/skitsanos/tiny-crew.git\ncd tiny-crew\nbun install\n```\n\n### Configuration\n\nCreate a `.env` file:\n\n```bash\nOPENAI_API_KEY=your_api_key_here\nDEFAULT_MODEL=gpt-4o\n```\n\n### Basic Example\n\n```typescript\nimport { Crew, Agent } from 'tiny-crew';\nimport OpenAI from 'openai';\n\nconst openai = new OpenAI();\n\n// Create a crew with a goal\nconst crew = new Crew({ goal: 'Research and summarize AI trends' }, openai);\n\n// Add specialized agents\ncrew.addAgent(new Agent({\n    name: 'Researcher',\n    goal: 'Find and analyze information',\n    capabilities: ['research', 'analysis']\n}, openai));\n\ncrew.addAgent(new Agent({\n    name: 'Writer',\n    goal: 'Create clear summaries',\n    capabilities: ['writing', 'summarization']\n}, openai));\n\n// Add tasks and execute\ncrew.addTask('Research recent AI breakthroughs');\ncrew.addTask('Summarize findings in 3 bullet points');\n\nawait crew.executeAllTasks();\nconst summary = await crew.achieveCrewGoal();\n```\n\n### Simple Agent Conversation\n\n```typescript\nconst agent = new Agent({\n    name: 'Assistant',\n    goal: 'Help users with questions'\n}, openai);\n\n// Conversations maintain history automatically\nconst response = await agent.chat('Hello!');\nconst followUp = await agent.chat('What can you help me with?');\n```\n\n## Documentation\n\nFull documentation is available in the [docs/](./docs/) folder:\n\n| Guide | Description |\n|-------|-------------|\n| [Getting Started](./docs/getting-started.md) | Installation, configuration, and first steps |\n| [Memory System](./docs/memory-system.md) | Knowledge sharing between agents |\n| [Multi-Model Routing](./docs/multi-model-routing.md) | Cost optimization with model routing |\n| [Conversation History](./docs/conversation-history.md) | Multi-turn conversations and summarization |\n| [Response Streaming](./docs/streaming.md) | Real-time response streaming |\n| [Agent Messaging](./docs/agent-messaging.md) | Agent-to-agent communication |\n| [Structured Output](./docs/structured-output.md) | Type-safe JSON responses with Zod schemas |\n| [Memory Tools](./docs/memory-tools.md) | Tools for agent memory management |\n| [Custom Tools](./docs/custom-tools.md) | Creating your own tools |\n| [Advanced Patterns](./docs/advanced-patterns.md) | Persona agents, behavioral modeling, structured protocols |\n| [Testing Guide](./docs/testing.md) | Mock clients and testing patterns |\n| [Use Cases](./docs/use-cases.md) | Practical implementation scenarios |\n\n## Examples\n\nThe `examples/` directory contains ready-to-run examples:\n\n```bash\nbun run examples/WebResearcher.ts\nbun run examples/CreativeWriter.ts\nbun run examples/PersistentMemory.ts\n```\n\n## Requirements\n\n- Bun (v1.2.x+) or Node.js (v22+)\n- TypeScript\n- OpenAI API key\n\n## Contributing\n\nContributions are welcome! Please feel free to submit a Pull Request.\n\n## License\n\nMIT License\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fskitsanos%2Ftiny-crew","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fskitsanos%2Ftiny-crew","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fskitsanos%2Ftiny-crew/lists"}