allenmaxi/contextgraph

上下文图

别再丢失经纪人的信息了。 ContextGraph 是编码代理和多代理团队的内存后端。 捕获持久事实，编译可信上下文包，并通过反应式检查点和仓库本地内存目录使代理状态可见。

反应性Δ型 · 上下文编译器· 使用场景· 演示 · 快速入门 · SDK · CLI · 更多使用场景 · 文档

英语 · 西班牙语

---

为什么它与众不同

大多数代理内存工具要么将原始文本存储在矢量数据库中，要么用一个有损摘要替代长会话。

ContextGraph 就是为这两者之间的差距而设计的：

• 受管理共享内存 使代理可以重复使用事实而不丢失来源、新度或访问控制
• 上下文包 让代理获得基于令牌预算的可解释上下文，而非晦涩的回忆结果
• 反应式δ压缩 让编码代理可以在上下文窗口关闭前检查点决策、打开任务、阻挡器和更改文件
• 分支感知上下文缓存，使子会话可以重复使用共享检查点前缀，而无需从头重新编译所有内容

ContextGraph

Stop losing agent context. ContextGraph is the memory backend for coding agents and multi-agent teams. Capture durable facts, compile trusted context packs, and make agent state visible with reactive checkpoints and repo-local memory directories.

Reactive Delta · Context Compiler · Use Cases · Demo · Quickstart · SDK · CLI · More Use Cases · Docs

English · Español

---

Why It Stands Out

Most agent memory tools either store raw text in a vector database or replace long sessions with one lossy summary.

ContextGraph is built for the gap between those two:

• governed shared memory so agents can reuse facts without losing provenance, freshness, or access control
• context packs so agents get token-budgeted, explainable context instead of opaque recall results
• reactive delta compaction so coding agents can checkpoint decisions, open tasks, blockers, and changed files before the context window collapses
• branch-aware context cache so child sessions can reuse shared checkpoint prefixes instead of recompiling everything from scratch
• .contextgraph/ memory directories so the latest session state is inspectable in the repo, not trapped inside one response payload

If you want memory that is inspectable, team-safe, and useful during real work, this is the wedge.

Start Here

The fastest path to understand the repo is:

1. run the 2-minute setup in examples/beta_quickstart.py
2. run the coding-agent continuity demo in examples/reactive_delta_compaction_demo.py
3. inspect the generated .contextgraph/ folder from that demo to see resume prompts, open tasks, failures, and branch/cache metadata
4. run the governed retrieval demo in examples/context_pack_demo.py