{"id":42382902,"url":"https://github.com/railtownai/railtracks","last_synced_at":"2026-04-01T17:57:01.334Z","repository":{"id":315140735,"uuid":"917852255","full_name":"RailtownAI/railtracks","owner":"RailtownAI","description":"An agentic framework that helps developers build resilient agentic systems","archived":false,"fork":false,"pushed_at":"2026-02-12T23:32:36.000Z","size":14146,"stargazers_count":113,"open_issues_count":124,"forks_count":5,"subscribers_count":1,"default_branch":"main","last_synced_at":"2026-02-13T03:56:59.541Z","etag":null,"topics":["ai","ai-agents","ai-agents-framework","framework","opensource","python"],"latest_commit_sha":null,"homepage":"http://railtracks.org/","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/RailtownAI.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":"CONTRIBUTING.md","funding":null,"license":"LICENSE","code_of_conduct":".github/CODE_OF_CONDUCT.md","threat_model":null,"audit":null,"citation":null,"codeowners":".github/CODEOWNERS","security":"SECURITY.md","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":"2025-01-16T19:07:24.000Z","updated_at":"2026-02-12T21:29:45.000Z","dependencies_parsed_at":"2025-09-17T00:20:27.670Z","dependency_job_id":"681e30b2-57ab-4f5b-b43e-df6c0db2eef1","html_url":"https://github.com/RailtownAI/railtracks","commit_stats":null,"previous_names":["railtownai/railtracks"],"tags_count":61,"template":false,"template_full_name":null,"purl":"pkg:github/RailtownAI/railtracks","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/RailtownAI%2Frailtracks","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/RailtownAI%2Frailtracks/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/RailtownAI%2Frailtracks/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/RailtownAI%2Frailtracks/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/RailtownAI","download_url":"https://codeload.github.com/RailtownAI/railtracks/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/RailtownAI%2Frailtracks/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":29634692,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-02-19T18:02:07.722Z","status":"ssl_error","status_checked_at":"2026-02-19T18:01:46.144Z","response_time":117,"last_error":"SSL_connect returned=1 errno=0 peeraddr=140.82.121.6:443 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":["ai","ai-agents","ai-agents-framework","framework","opensource","python"],"created_at":"2026-01-27T22:27:40.776Z","updated_at":"2026-04-01T17:57:01.295Z","avatar_url":"https://github.com/RailtownAI.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Railtracks\n\n\u003cp align=\"center\"\u003e\n  \u003cimg alt=\"Railtracks\" src=\"https://railtracksstorage.blob.core.windows.net/railtrackswebsite/images/logo.svg\" width=\"40%\"\u003e\n\u003c/p\u003e\n\u003cbr\u003e\n\n\u003cp align=\"center\"\u003e\n  \u003ca href=\"https://pypi.org/project/railtracks/\"\u003e\n    \u003cimg src=\"https://img.shields.io/pypi/v/railtracks?color=brightgreen\u0026style=for-the-badge\" alt=\"PyPI Version\" /\u003e\n  \u003c/a\u003e\n  \u003ca href=\"https://pypi.org/project/railtracks/\"\u003e\n    \u003cimg src=\"https://img.shields.io/pypi/pyversions/railtracks?style=for-the-badge\u0026logo=python\u0026logoColor=white\" alt=\"Python Versions\" /\u003e\n  \u003c/a\u003e\n  \u003ca href=\"https://pypistats.org/packages/railtracks\"\u003e\n    \u003cimg src=\"https://img.shields.io/pypi/dm/railtracks?style=for-the-badge\u0026color=blue\" alt=\"Monthly Downloads\" /\u003e\n  \u003c/a\u003e\n  \u003ca href=\"https://opensource.org/licenses/MIT\"\u003e\n    \u003cimg src=\"https://img.shields.io/pypi/l/railtracks?style=for-the-badge\u0026color=lightgrey\" alt=\"License\" /\u003e\n  \u003c/a\u003e\n  \u003ca href=\"https://github.com/RailtownAI/railtracks/stargazers\"\u003e\n    \u003cimg src=\"https://img.shields.io/github/stars/RailtownAI/railtracks?style=for-the-badge\u0026logo=github\" alt=\"GitHub Stars\" /\u003e\n  \u003c/a\u003e\n\u003c/p\u003e\n\n\u003cdiv align=\"center\"\u003e\n\n\u003c/div\u003e\n\n## What is Railtracks?\n\nRailtracks is a Python framework for building agentic systems. Agent behavior, tools, and multi-step flows are defined entirely in standard Python using the control flow and abstractions you already know.\n\n\n```python\nimport railtracks as rt\n\n# Define a tool (just a function!)\ndef get_weather(location: str) -\u003e str:\n    return f\"It's sunny in {location}!\"\n\n# Create an agent with tools\nagent = rt.agent_node(\n    \"Weather Assistant\",\n    tool_nodes=(rt.function_node(get_weather)),\n    llm=rt.llm.OpenAILLM(\"gpt-4o\"),\n    system_message=\"You help users with weather information.\"\n)\n\n# Run it\nflow = rt.Flow(name=\"Weather Flow\", entry_point=agent)\nresult = flow.invoke(\"What's the weather in Paris?\")\n# or `await flow.ainvoke(\"What's the weather in Paris?)` in an async context\nprint(result.text)  # \"Based on the current data, it's sunny in Paris!\"\n```\n\nExecution order, branching, and looping are expressed using standard Python control flow.\n\n## Why Railtracks?\n\n\u003cdiv align=\"center\"\u003e\n\n\u003ctable\u003e\n\u003ctr\u003e\n\u003ctd width=\"50%\" valign=\"top\"\u003e\n\n#### Pure Python\n```python\n# Write agents like regular functions\n@rt.function_node\ndef my_tool(text: str) -\u003e str:\n    return process(text)\n```\n- No YAML, no DSLs, no magic strings\n- Compatible with standard debuggers\n- Full IDE autocomplete and type checking\n\n\u003c/td\u003e\n\u003ctd width=\"50%\" valign=\"top\"\u003e\n\n#### Tool-First Architecture\n```python\n# Any function becomes a tool\nagent = rt.agent_node(\n    \"Assistant\",\n    tool_nodes=[my_tool, api_call]\n)\n```\n- Automatic function-to-tool conversion\n- Seamless API and database integration\n- MCP protocol support\n\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd width=\"50%\" valign=\"top\"\u003e\n\n#### Familiar Interface\n```python\n# Native Async support\nresult = await rt.call(agent, query)\n```\n- Standardized `call` interface, consistent with asyncio patterns\n- Built-in validation, error handling, and retries\n- Automatic parallelization management\n\n\u003c/td\u003e\n\u003ctd width=\"50%\" valign=\"top\"\u003e\n\n#### Built-in Observability\n\nRailtracks includes a visualizer for inspecting agent runs and evaluations in real-time, run completely locally with no signups required.\n\nSee the [Observability documentation](https://railtownai.github.io/railtracks/observability/visualization/) for setup and usage.\n\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003c/table\u003e\n\n\u003c/div\u003e\n\n## Quick Start\n\n\u003cdetails open\u003e\n\u003csummary\u003e\u003cb\u003eInstallation\u003c/b\u003e\u003c/summary\u003e\n\n```bash\npip install railtracks 'railtracks[cli]'\n```\n\u003c/details\u003e\n\n\n\u003cdetails open\u003e\n\u003csummary\u003e\u003cb\u003eYour First Agent\u003c/b\u003e\u003c/summary\u003e\n\n\n```python\nimport railtracks as rt\n\n# 1. Create tools (just functions with decorators!)\n@rt.function_node\ndef count_characters(text: str, character: str) -\u003e int:\n    \"\"\"Count occurrences of a character in text.\"\"\"\n    return text.count(character)\n\n@rt.function_node\ndef word_count(text: str) -\u003e int:\n    \"\"\"Count words in text.\"\"\"\n    return len(text.split())\n\n# 2. Build an agent with tools\ntext_analyzer = rt.agent_node(\n    \"Text Analyzer\",\n    tool_nodes=(count_characters, word_count),\n    llm=rt.llm.OpenAILLM(\"gpt-4o\"),\n    system_message=\"You analyze text using the available tools.\"\n)\n\n# 3. Use it to solve the classic \"How many r's in strawberry?\" problem\ntext_flow = rt.Flow(\n  name=\"Text Analysis Flow\"\n  entry_point=text_analyzer\n)\n\ntext_flow.invoke(\"How many 'r's are in 'strawberry'?\")\n```\n\n\u003c/details\u003e\n\n\n## LLM Support\n\nRailtracks integrates with major model providers through a unified interface:\n\n```python\n# OpenAI\nrt.llm.OpenAILLM(\"gpt-5\")\n\n# Anthropic\nrt.llm.AnthropicLLM(\"claude-4-6-sonnet\")\n\n# Local models\nrt.llm.OllamaLLM(\"llama3\")\n```\n\nWorks with **OpenAI**, **Anthropic**, **Google**, **Azure**, and more. See the [full provider list](https://railtownai.github.io/railtracks/llm_support/providers/).\n\n## Contributing\n\nRailtracks is developed in the open. Contributions, bug reports, and feature requests are welcome via [GitHub Issues](https://github.com/RailtownAI/railtracks/issues).\n\n\u003cp align=\"center\"\u003e\n  \u003ca href=\"https://railtownai.github.io/railtracks/quickstart/quickstart/\"\u003e\n    \u003cimg src=\"https://img.shields.io/badge/Quick_Start-4285F4?style=for-the-badge\u0026logo=rocket\u0026logoColor=white\" alt=\"Quick Start\" /\u003e\n  \u003c/a\u003e\n  \u003ca href=\"https://railtownai.github.io/railtracks/\"\u003e\n    \u003cimg src=\"https://img.shields.io/badge/Documentation-00D4AA?style=for-the-badge\u0026logo=gitbook\u0026logoColor=white\" alt=\"Documentation\" /\u003e\n  \u003c/a\u003e\n  \u003ca href=\"https://github.com/RailtownAI/railtracks/tree/main/examples\"\u003e\n    \u003cimg src=\"https://img.shields.io/badge/Examples-FF6B35?style=for-the-badge\u0026logo=github\u0026logoColor=white\" alt=\"Examples\" /\u003e\n  \u003c/a\u003e\n  \u003ca href=\"https://discord.gg/2JUb2TxjJv\"\u003e\n    \u003cimg src=\"https://img.shields.io/badge/Discord-5865F2?style=for-the-badge\u0026logo=discord\u0026logoColor=white\" alt=\"Join Discord\" /\u003e\n  \u003c/a\u003e\n\u003c/p\u003e\n\n---\n\n\u003csub\u003eLicensed under MIT · Made by the Railtracks team\u003c/sub\u003e","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Frailtownai%2Frailtracks","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Frailtownai%2Frailtracks","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Frailtownai%2Frailtracks/lists"}