Query and curate project knowledge in a local ByteRover context tree.
npx skills add https://github.com/papachong/RHClaw --skill byterover-papachong
Please help me install this Agent Skill. Skill: byterover Source: https://github.com/papachong/RHClaw/tree/main/RHClaw-Desktop/src-tauri/skills/byterover Command: npx skills add https://github.com/papachong/RHClaw --skill byterover-papachong
Many projects and AI agents lack a reliable, versioned local memory of architectural decisions, patterns, and project-specific rules, causing repeated work, inconsistent decisions, and lost context across tasks.
Run a brv query to retrieve existing architectural decisions and then run a brv curate to save new patterns after your change.
High-intent search queries and answers about installing and using this skill.
You can persist project knowledge by storing architectural decisions and patterns as human-readable Markdown files within a local .brv/context-tree. This provides a versioned local memory for AI agents to query before taking action and to curate after implementing changes.
Local knowledge management for AI agents is handled through command-line operations that query existing context before development and curate new patterns afterward. The system uses a local context tree to prevent lost context and inconsistent decisions across tasks.
You do not need a specific LLM provider because ByteRover is configured as the default no-key provider. The system supports configurable LLM providers, requiring only a configured provider and the byterover-cli installed to retrieve project context.
You save new design patterns by running a brv curate command after your changes. This command stores the final decisions and supporting files back into the local .brv/context-tree knowledge base for future recall.
Your developer team can sync local project memory using the optional authenticated cloud sync feature. This allows teams to share the curated architectural decisions and project context stored in the local knowledge tree.
AI agents repeat work and lose context across tasks due to the lack of a reliable, versioned local memory of architectural decisions and project-specific rules. Establishing a local context tree solves this by enabling recall and curation.
irahardiantoRetrieve implementation knowledge, code examples, and documentation references from a knowledge base.
AvinavaOrganize Salesforce Life Sciences Cloud Developer Guide topics into structured Markdown knowledge.
thisismynewfmail-uiConfigure and operate the Monika AI agent across terminals and messaging gateways.
caobingshengCoordinate dynamic AI context management across memory, tools, and retrieval systems.
