$ loading_
Manage directory-scoped memory for AI coding agents to cut token usage.
Copy the install command and let the AI configure it · recommended for beginners
No copy-paste install info for "ham" yet — see the docs or source repo.
Use HAM to create directory-level memory rules for this multi-folder project. Only load relevant context when I edit backend/api, and explain how this reduces token usage.
A directory-scoped memory plan with loading rules for backend/api and an explanation of token savings.
Help me design a HAM memory structure for a large repository with frontend, backend, and infra, defining the long-term context to retain for each directory.
A directory-based memory structure detailing key retained information and invocation boundaries for each module.
Analyze how my AI coding agent repeatedly reads context across the project, and suggest how to use HAM to reduce token costs by about 80%.
An analysis of the issue, HAM implementation steps, and expected context reduction and cost optimization outcomes.
Give AI agents persistent memory across sessions with efficient on-demand context loading.
Give AI coding agents persistent cross-project memory and connected context retrieval.
Give AI coding agents persistent memory across sessions for people, decisions, and context.
Provides local persistent memory for coding agents with low-cost context retrieval.
Give AI coding agents persistent memory for project context and decisions.
Provide structured memory and intent capture for AI agents with lower token costs.