{"id":51508544,"url":"https://github.com/blackwell-systems/gcf-n8n-nodes","last_synced_at":"2026-07-08T03:30:38.557Z","repository":{"id":365054407,"uuid":"1270344412","full_name":"blackwell-systems/gcf-n8n-nodes","owner":"blackwell-systems","description":"n8n node for GCF (Graph Compact Format) - bidirectional JSON/GCF conversion. 71% fewer tokens, zero config.","archived":false,"fork":false,"pushed_at":"2026-06-15T18:03:37.000Z","size":7,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":0,"default_branch":"main","last_synced_at":"2026-06-15T18:13:17.425Z","etag":null,"topics":["ai","gcf","llm","n8n","n8n-community-node-package","token-efficiency","workflow-automation"],"latest_commit_sha":null,"homepage":null,"language":"TypeScript","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/blackwell-systems.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":"2026-06-15T16:11:07.000Z","updated_at":"2026-06-15T18:03:41.000Z","dependencies_parsed_at":null,"dependency_job_id":null,"html_url":"https://github.com/blackwell-systems/gcf-n8n-nodes","commit_stats":null,"previous_names":["blackwell-systems/gcf-n8n-nodes"],"tags_count":1,"template":false,"template_full_name":null,"purl":"pkg:github/blackwell-systems/gcf-n8n-nodes","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/blackwell-systems%2Fgcf-n8n-nodes","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/blackwell-systems%2Fgcf-n8n-nodes/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/blackwell-systems%2Fgcf-n8n-nodes/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/blackwell-systems%2Fgcf-n8n-nodes/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/blackwell-systems","download_url":"https://codeload.github.com/blackwell-systems/gcf-n8n-nodes/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/blackwell-systems%2Fgcf-n8n-nodes/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":35251015,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-05-26T15:22:16.424Z","status":"online","status_checked_at":"2026-07-08T02:00:06.796Z","response_time":61,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"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","gcf","llm","n8n","n8n-community-node-package","token-efficiency","workflow-automation"],"created_at":"2026-07-08T03:30:37.895Z","updated_at":"2026-07-08T03:30:38.547Z","avatar_url":"https://github.com/blackwell-systems.png","language":"TypeScript","funding_links":[],"categories":[],"sub_categories":[],"readme":"# n8n-nodes-gcf\n\nn8n community node for [GCF (Graph Compact Format)](https://gcformat.com) -- bidirectional conversion between GCF and JSON with 71% fewer tokens and zero config.\n\nGCF is a structured data wire format optimized for LLM tool responses. It achieves 90.7% comprehension across 10 models while cutting token costs by 71% compared to JSON.\n\n## Installation\n\nIn your n8n instance:\n\n```bash\nnpm install n8n-nodes-gcf\n```\n\nOr install via the n8n UI: **Settings \u003e Community Nodes \u003e Install \u003e `n8n-nodes-gcf`**\n\n## Operations\n\n### Encode (JSON to GCF)\n\nConverts JSON input to GCF format. Automatically detects whether to use the graph profile (for tool payloads with `tool` + `symbols` fields) or the generic profile (everything else).\n\n- **Input Data**: Drag and drop JSON data, use `{{ $json }}`, or reference a field name\n- **Output Field**: Field name for the GCF output (default: `data`)\n- **Include Token Metrics**: Adds estimated token counts for JSON vs GCF with reduction percentage\n\n### Decode (GCF to JSON)\n\nParses GCF text back into JSON. Automatically detects graph vs generic profile from the header.\n\n- **Input Data**: A GCF-formatted string (field reference or literal text)\n- **Output Field**: Field name for the JSON output (default: `data`)\n\n## AI Agent Integration\n\nThis node has `usableAsTool: true`, so n8n AI agents can use it directly to compress tool responses before sending them to the LLM, saving tokens on every call.\n\n## Example Workflow\n\n1. **HTTP Request** node fetches API data (JSON)\n2. **GCF** node encodes it to GCF (Encode operation)\n3. **AI Agent** node receives the compressed payload, saving 71% on input tokens\n4. **GCF** node decodes agent output back to JSON (Decode operation)\n\n## Token Savings\n\nEnable \"Include Token Metrics\" to see per-item comparisons:\n\n```json\n{\n  \"data\": \"GCF profile=generic\\n...\",\n  \"tokenMetrics\": {\n    \"jsonTokens\": 1200,\n    \"gcfTokens\": 350,\n    \"tokensSaved\": 850,\n    \"reductionPercent\": 70.83\n  }\n}\n```\n\n## Links\n\n- [GCF Specification](https://gcformat.com)\n- [Interactive Playground](https://gcformat.com/playground)\n- [Benchmark Results](https://gcformat.com/guide/benchmarks)\n- [GitHub](https://github.com/blackwell-systems/gcf-n8n-nodes)\n- [GCF TypeScript Library](https://www.npmjs.com/package/@blackwell-systems/gcf)\n\n## Why GCF over TOON?\n\n| | GCF | TOON |\n|---|---|---|\n| Token savings vs JSON | **71%** | 40% |\n| GCF vs TOON (15 datasets) | **25.5% fewer** | baseline |\n| LLM comprehension (500 records) | **100%** on every frontier model | Fails on GPT-5.5 |\n| LLM generation validity | **5/5** on every frontier model | Rejected by 7/9 models |\n| Source format support | JSON, YAML, TOML, CSV, MessagePack | JSON only |\n| Runtime dependencies | **Zero** | 1 |\n| Lossless round-trips verified | **33 billion+** | None published |\n| Session deduplication | Yes (92% savings by 5th call) | No |\n| Graph/relationship encoding | Yes (local IDs, typed edges) | No |\n\n[Full comparison with benchmarks](https://gcformat.com/guide/vs-toon.html)\n\n## How GCF Works\n\nGCF replaces JSON's verbose syntax with a compact, deterministic encoding:\n\n- No braces, brackets, or quotes for keys\n- Tabular arrays encoded as pipe-separated rows\n- Nested structures via indentation\n- Zero config: `encodeGeneric(data)` and `decodeGeneric(text)` handle everything\n\nThe encoding is fully deterministic and round-trip safe.\n\n## License\n\nMIT\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fblackwell-systems%2Fgcf-n8n-nodes","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fblackwell-systems%2Fgcf-n8n-nodes","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fblackwell-systems%2Fgcf-n8n-nodes/lists"}