<p align="center">
<a href="https://github.com/blackwell-systems"><img src="https://raw.githubusercontent.com/blackwell-systems/blackwell-docs-theme/main/badge-trademark.svg" alt="Blackwell Systems"></a>
<a href="https://github.com/blackwell-systems/gcf-rust/actions"><img src="https://github.com/blackwell-systems/gcf-rust/actions/workflows/ci.yml/badge.svg" alt="CI"></a>
<a href="LICENSE"><img src="https://img.shields.io/badge/license-MIT-blue.svg" alt="License"></a>
<a href="https://crates.io/crates/gcf"><img src="https://img.shields.io/crates/v/gcf.svg" alt="crates.io"></a>
</p>
# gcf-rust
Rust implementation of [GCF (Graph Compact Format)](https://gcformat.com/) -- the most token-efficient wire format for LLMs. A drop-in alternative to JSON and TOON for any structured data.
**79% fewer input tokens than JSON. 75% fewer output tokens. 52% smaller than TOON. 100% LLM comprehension at 500 symbols, where JSON fails at 66.7%.**
## Install
```toml
[dependencies]
gcf = "0.1"
```
Zero-copy where possible. Minimal dependencies (serde, serde_json). Don't want to change code? Use the [MCP proxy](https://github.com/blackwell-systems/gcf-proxy) for zero-code adoption.
## Quick Start
```rust
use gcf::{Payload, Symbol, Edge, encode, decode};
let p = Payload {
tool: "context_for_task".to_string(),
token_budget: 5000,
tokens_used: 1847,
pack_root: String::new(),
symbols: vec![
Symbol {
qualified_name: "pkg.AuthMiddleware".to_string(),
kind: "function".to_string(),
score: 0.78,
provenance: "lsp_resolved".to_string(),
distance: 0,
signature: String::new(),
components: Default::default(),
},
Symbol {
qualified_name: "pkg.NewServer".to_string(),
kind: "function".to_string(),
score: 0.54,
provenance: "lsp_resolved".to_string(),
distance: 1,
signature: String::new(),
components: Default::default(),
},
],
edges: vec![Edge {
source: "pkg.NewServer".to_string(),
target: "pkg.AuthMiddleware".to_string(),
edge_type: "calls".to_string(),
status: String::new(),
}],
};
let output = encode(&p);
```
Output:
```
GCF tool=context_for_task budget=5000 tokens=1847 symbols=2
## targets
@0 fn pkg.AuthMiddleware 0.78 lsp_resolved
## related
@1 fn pkg.NewServer 0.54 lsp_resolved
## edges
@0<@1 calls
```
## Decode
```rust
use gcf::decode;
let p = decode(input).expect("valid GCF");
println!("{} {} symbols {} edges", p.tool, p.symbols.len(), p.edges.len());
```
## Session Deduplication
Track transmitted symbols across multiple tool responses. Previously-sent symbols become bare references instead of full declarations:
```rust
use gcf::{Session, encode_with_session};
let sess = Session::new();
let out1 = encode_with_session(&payload1, &sess); // full declarations
let out2 = encode_with_session(&payload2, &sess); // reused symbols as "@N # previously transmitted"
```
By the 5th call in a session: 92.7% token savings vs JSON.
## Delta Encoding
When the consumer already has a prior context pack, send only what changed:
```rust
use gcf::{DeltaPayload, Symbol, encode_delta};
let delta = DeltaPayload {
tool: "context_for_task".to_string(),
base_root: "aaa111".to_string(),
new_root: "bbb222".to_string(),
removed: vec![Symbol {
qualified_name: "pkg.OldFunc".to_string(),
kind: "function".to_string(),
score: 0.0,
provenance: String::new(),
distance: 0,
signature: String::new(),
components: Default::default(),
}],
added: vec![Symbol {
qualified_name: "pkg.NewFunc".to_string(),
kind: "function".to_string(),
score: 0.85,
provenance: "rwr".to_string(),
distance: 0,
signature: String::new(),
components: Default::default(),
}],
removed_edges: vec![],
added_edges: vec![],
delta_tokens: 30,
full_tokens: 200,
};
let output = encode_delta(&delta);
```
81.2% savings on re-queries where the pack changed slightly.
## Generic Encoding
Encode any `serde_json::Value` (not just graph payloads) into GCF tabular format:
```rust
use gcf::encode_generic;
use serde_json::json;
let data = json!({
"employees": [
{"id": 1, "name": "Alice", "department": "Engineering", "salary": 95000},
{"id": 2, "name": "Bob", "department": "Sales", "salary": 72000},
],
});
let output = encode_generic(&data);
```
Output:
```
## employees [2]{department,id,name,salary}
```
Works on objects, arrays, and primitives. Arrays of uniform objects get tabular rows. Nested objects use `## key` section headers.
## API
| `encode(p: &Payload) -> String` | Encode a graph payload to GCF text |
| `encode_generic(data: &Value) -> String` | Encode any JSON value to GCF tabular format |
| `decode(input: &str) -> Result<Payload, DecodeError>` | Parse GCF text back to a Payload |
| `encode_with_session(p: &Payload, s: &Session) -> String` | Encode with session deduplication |
| `encode_delta(d: &DeltaPayload) -> String` | Encode a delta (added/removed only) |
| `Session::new() -> Session` | Create a new session tracker (thread-safe via Mutex) |
## Types
| `Payload` | Full GCF payload: tool, budget, symbols, edges, pack root |
| `Symbol` | Graph node: qualified name, kind, score, provenance, distance |
| `Edge` | Directed relationship: source, target, edge type |
| `DeltaPayload` | Diff between two packs: added/removed symbols and edges |
| `Components` | Score breakdown: blast_radius, confidence, recency, distance |
| `Session` | Thread-safe tracker for multi-call deduplication |
| `DecodeError` | Enum of decode failure modes |
## Benchmarks
```bash
cargo bench
```
## Links
- [Documentation](https://gcformat.com/)
- [Playground](https://gcformat.com/playground.html)
- [Specification](https://github.com/blackwell-systems/gcf)
- [Go library](https://github.com/blackwell-systems/gcf-go)
- [TypeScript library](https://github.com/blackwell-systems/gcf-typescript)
- [Python library](https://github.com/blackwell-systems/gcf-python)
- [MCP Proxy](https://github.com/blackwell-systems/gcf-proxy) (zero-code adoption)
- [GCF vs TOON](https://gcformat.com/guide/vs-toon.html)
## License
MIT