{"id":32861802,"url":"https://github.com/theirish81/frags","last_synced_at":"2026-05-13T16:01:35.320Z","repository":{"id":322838092,"uuid":"1090991395","full_name":"theirish81/frags","owner":"theirish81","description":"Frags is an advanced AI agent for complex data workflows—retrieval, transformation, extraction, and aggregation. Highly customizable and extensible, it prioritizes precision.","archived":false,"fork":false,"pushed_at":"2026-01-24T17:04:55.000Z","size":435,"stargazers_count":6,"open_issues_count":2,"forks_count":1,"subscribers_count":2,"default_branch":"main","last_synced_at":"2026-01-24T23:26:49.199Z","etag":null,"topics":["agent","agentic-ai","ai","golang","json-schema","llm"],"latest_commit_sha":null,"homepage":"","language":"Go","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"agpl-3.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/theirish81.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":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":"2025-11-06T12:11:58.000Z","updated_at":"2026-01-24T16:50:50.000Z","dependencies_parsed_at":null,"dependency_job_id":null,"html_url":"https://github.com/theirish81/frags","commit_stats":null,"previous_names":["theirish81/frags"],"tags_count":101,"template":false,"template_full_name":null,"purl":"pkg:github/theirish81/frags","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/theirish81%2Ffrags","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/theirish81%2Ffrags/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/theirish81%2Ffrags/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/theirish81%2Ffrags/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/theirish81","download_url":"https://codeload.github.com/theirish81/frags/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/theirish81%2Ffrags/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":28810475,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-01-27T07:41:26.337Z","status":"ssl_error","status_checked_at":"2026-01-27T07:41:08.776Z","response_time":168,"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":["agent","agentic-ai","ai","golang","json-schema","llm"],"created_at":"2025-11-08T22:00:31.232Z","updated_at":"2026-01-27T09:18:53.472Z","avatar_url":"https://github.com/theirish81.png","language":"Go","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Welcome to Frags\n**Note:** The project is still in development, but you can already try it out.\n\n## What is Frags?\nFrags is an advanced AI/LLM Agent dedicated to executing complex workflows of data retrieval, transformation, extraction\nand aggregation. It is designed to be highly customizable and extensible, allowing you to integrate it with your own\ntools and processes. Its main goal is **precision and focus**, and it's a **system** dedicated to engineers and\nspecialists rather than a *code-free quick fix*.\n\nFrags comes as a **CLI tool** and as a **library to be integrated into Golang projects**.\n\n### Main features\n* **Multi LLM:** Frags supports multiple LLMs, allowing you to choose the one that best suits your needs.\n* **Dedicated almost exclusively to producing structured content:** the purpose of Frags is to be integrated in advanced\n  workflows, therefore its output needs to be perfectly predictable and consumable by a machine.\n* **Orchestration system:** Frags **is not** an agent to which you ask a question a simple answer back. The  whole\n  purpose of Frags is to allow the user to describe complex data retrieval, transformation, extraction and  aggregation\n  to produce complex data structures.\n* **Advanced support for tools:** Frags has a whole standardized system to integrate with internal (as in: provided by\n  the integrator) and external tools (as in: MCP servers).\n* **Anti-context-bloating:** Frags multi-session system allows you to define and organize what is present in the LLM\n  context, based on the session task, improving focus and reducing the risk of hallucinations\n* **Output segmentation:** Frags allows you to segment your output into multiple parts, allowing you to overcome\n  output token limitations, and improving answer quality.\n* **Advanced pre/post-processing:** Frags allows you to define custom pre/post-processing steps, scripts, tools, and\n  transformers, reducing the amount of LLM work where not necessary, reducing cost, improving performance and answer\n  quality.\n* **Modularity:** Frags is designed to be easily extensible, allowing you to add new features and integrate them with\n  your own tools.\n\n### Use cases\n* **Research/Paper:** when your needs go beyond getting a straight answer, but need a whole structured research\n  on sophisticated topics. The context reduction, focus enhancement, document ingestion combined with internet search\n  allows you to design how your paper should contain in each section, allowing the LLM to focus on each  objective and\n  produce data you can process however you want.\n* **Data extraction:** Frags allows you to define complex data extraction pipelines, allowing you to extract data from\n  documents, making sure the output is structured and predictable. This makes it easy to plug into other systems that\n  expect predefined fields and values.\n* **Data transformation/analysis:** From data retrieval (via the Internet, databases or any MCP tool available) to\n  analysis or transformation, Frags can guide the process and provide solid data structures, skimming the context and\n  increasing the credibility of the results.\n* **Reporting:** Connect Frags to data sources and define complex reporting templates that describe the entire status\n  of a system, division or company. Connect the output to a reporting tool to produce quality reports.\n* **Notes augmentation:** give Frags your notes and design how you want the LLM to expand them into a fully featured\n  document.\n* **Chatbot augmentation:** improve your chatbot from an \"answers machine\" to an \"explanation engine.\"\n* **Creative writing:** Frags can be used to generate creative content, allowing you to design how your writing should\n  look like, and how it should be structured.\n\n## Find the full documentation in the [Frags Wiki](https://github.com/theirish81/frags/wiki)","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Ftheirish81%2Ffrags","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Ftheirish81%2Ffrags","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Ftheirish81%2Ffrags/lists"}