Agent
Define the .limps/ workspace structure and implement initialization.
limps your Local Intelligent MCP Planning Server across AI assistants. No subscriptions, no cloud—run it locally. Version control your planning docs in git. No more context drift—one shared source of truth across Claude, Cursor, Copilot, and any MCP tool.
Agent
Define the .limps/ workspace structure and implement initialization.
Agent
Build the context inheritance engine that resolves cascading context from workspace → project → plan → agent.
Agent
Implement persistent memory for agents that survives across sessions.
Agent
Implement plan-level shared memory for cross-agent learnings.
Agent
Detect stale context files and surface freshness warnings.
Agent
Track when documents supersede others, maintaining decision history chains.
Agent
Detect and surface conflicts in inherited context.
Agent
Integrate context hierarchy with Plan 0042's knowledge graph.
Agent
Document the context hierarchy and memory system comprehensively.
Agent
Harden the MCP server session lifecycle: auto-reconnect, graceful shutdown, session persistence across restarts.
Agent
Create a reusable McpClientManager class that wraps StreamableHTTPClientTransport with connection pooling, auto-reconnect, and health monitoring.
Agent
Integrate McpClientManager into the Obsidian plugin, replacing CLI-based communication with persistent MCP sessions.
Agent
Build typed wrapper functions around MCP tool calls for use in the Obsidian plugin, providing a clean API surface.
Agent
Implement Obsidian commands for creating, editing, and navigating planning documents via MCP tools.
Agent
Build Obsidian UI for viewing and managing agent tasks, including status updates and progress tracking.
Agent
Create search modals for full-text plan search and a proposals UI for reviewing and applying suggested changes.
Agent
Implement presence-aware indexing for 60GB+ scale vaults, knowing files exist without parsing, with smart default exclusions.
Agent
Support multiple plan paths in configuration with a streaming scanner for efficient file discovery.
Agent
Add scheduled health checks for the MCP connection and vault automation for periodic re-indexing and status updates.
Agent
Automatically apply approved proposals and notify users of new proposals, conflicts, or status changes.
Agent
Analyze document structure and build cross-document link graphs for dependency tracking and navigation.
Agent
Detect conflicts between plans and agents, and discover implicit relationships across the planning corpus.
Agent
Write user-facing and developer documentation for the deep integration features, setup guides, and API references.
Agent
Build integration tests and end-to-end validation for the full Obsidian deep integration pipeline.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: