Memory layer for AI Agents. Replace complex RAG pipelines with a serverless, single-file memory layer. Give your agents instant retrieval and long-term memory.

From anywhere you can type, query and stream the output of any script (e.g. an LLM)

Compress LLM context to save tokens and reduce costs

Smart Tree: not just a tree, a philosophy. A context-aware, AI-crafted replacement for 20+ tools with MEM8 quantum compression, semantic search, AST-smart editing, and partnership memory. Crafted with care by human + AI—accept no knock-offs.

High-quality search for AI-native applications.

快速陷入处理

A forward proxy to turn network traffic into personal memory for AI agents

A typed map which can make sure item exist.

Convert webpages to clean markdown

CodeMerge is useful for consolidating code from various files into a single file that can be used as context for AI code generation models. By merging relevant code and passing it to an LLM, the model can generate more accurate and contextually relevant code snippets.

A Rust error crate with the goal of identifying precisely where and in which context an error occurs.

Safeguard for kubectl

OpenFused is a shared memory and messaging layer for AI agents, built on plain files. It gives agents persistent context, signed mail, and peer sync without locking them into a proprietary runtime.

A Rust CLI tool that transforms your project files into perfectly formatted context blocks for Large Language Models. Ideal for code reviews, refactoring assistance, and technical discussions with AI.

Any storage. Any agent. One CLI

Like git stash, but for your agent's working memory.

Manage mixed repositories

The 'Blast Radius' detector for AI Agents. Prevent regressions using Git history and organizational memory.

This provides stackful coroutines.

Repository intelligence for agentic development