★ 368 Rust MIT sse 更新 47分钟前

Cersei

The Rust SDK for building coding agents. Tool execution, LLM streaming, graph memory, sub-agent orchestration, MCP — as composable library functions.

GitHub 官网

安装配置

暂未识别到可直接复制的 MCP 配置，请查看 GitHub README。后台管理员可以补充配置。

README 摘要

# Cersei The complete Rust SDK for building coding agents. Cersei gives you every building block of a production coding agent — tool execution, LLM streaming, sub-agent orchestration, persistent memory, skills, MCP integration — as composable library functions. Build a Claude Code replacement, embed an agent in your app, or create something entirely new. ```rust use cersei::prelude::*; #[tokio::main] async fn main() -> anyhow::Result { let output = Agent::builder() .provider(Anthropic::from_env()?) .tools(cersei::tools::coding()) .permission_policy(AllowAll) .run_with("Fix the failing tests in src/") .await?; println!("{}", output.text()); Ok(()) } ``` **MIT License** | Built by [Adib Mohsin](https://github.com/pacifio) | [Docs](https://cersei.pacifio.dev/docs) | [GitHub](https://github.com/pacifio/cersei) --- ## Why Cersei | | Claude Code | OpenCode | **Cersei SDK** | **Abstract CLI** | |---|---|---|---|---| | Form factor | CLI app | CLI app | **Library** | **CLI app** | | Embeddable | No | No | **Yes** | No (uses SDK) | | Provider | Anthropic only | Multi-provider | **Multi-provider** | **Multi-provider** | | Language | TypeScript | TypeScript | **Rust** | **Rust** | | Custom tools | Plugins | Plugins | **`impl Tool` / `#[derive(Tool)]`** | Via SDK | | Startup | ~269ms | ~300ms | N/A (library) | **~34ms** | | Binary / RSS | 174MB / 330MB | — | N/A | **5.8MB / 4.9MB** | | Memory | File-based | SQLite | **File + Graph** | **File + Graph** | | Skills | `.claude/commands/` | `.claude/skills/` | **Both formats** | **Both formats** | Cersei is built from the architecture of Claude Code (reverse-engineered Rust port) and designed so that anyone can build a complete, drop-in replacement for Claude Code, OpenCode, or any coding agent — as a library call. --- ## Abstract — The CLI **Abstract** is a complete CLI coding agent built on Cersei. One binary, zero runtime dependencies, graph memory by default. ```bash # Install cargo install --path crates/abstract-cli # Use abstract # Interactive REPL abstract "fix the failing tests" # Single-shot abstract --resume # Resume last session abstract --model opus --max # Opus with max thinking abstract --no-permissions --json # CI mode with NDJSON output ``` ### Abstract vs Claude Code All numbers from `run_tool_bench.sh --full`. | Metric | Abstract | Claude Code | Winner | |--------|----------|-------------|--------| | Startup (warm) | **32ms** | 266ms | Abstract (8.2x) | | Binary size | **6.0 MB** | 174 MB | Abstract (29x) | | Memory (RSS) | **4.9 MB** | 333 MB | Abstract (68x) | | Tool dispatch | **0.02-17ms** | 5-265ms+ | Abstract | | Memory recall | **98us** (graph) | 7,545ms (LLM) | Abstract (77,000x) | | Memory write | **30us** (graph) | 20,687ms (agent) | Abstract (689,000x) | | MEMORY.md load | **9.6us** | 17.1ms | Abstract (1,781x) | | Sequential throughput | **906ms/req** | 12,079ms/req | Abstract (13.3x) | | System prompt tokens | **~2,200** | ~8,000+ | Abstract (3.6x fewer) | | LLM call for recall | **Not needed** | Required (Sonnet) | Abstract | > Claude Code's memory recall calls Sonnet every turn to rank the top 5 files by relevance (7.5s measured). > Abstract's graph does indexed lookups in 98 microseconds — same capability, no LLM call, no API cost. Full benchmark: [`crates/abstract-cli/benchmarks/REPORT.md`](crates/abstract-cli/benchmarks/REPORT.md) ### Features...

Cersei

安装配置

README 摘要

相关 MCP

Awesome S

Chrome Devtools

Libre Chat

Playwright

Github

Fast