Commit Graph

9 Commits

Author SHA1 Message Date
ved015 968a7c2110 Unify agent memories in stable repository containers 2026-07-14 09:44:12 +05:30
Sreeram Sreedhar 3a0c34c169 add baseUrl to config 2026-06-10 12:22:24 -07:00
ved015 04099701ce feat: add claude supermemory status command
Co-authored-by: Cursor <cursoragent@cursor.com>
2026-06-04 18:06:47 +05:30
Mahesh Sanikommu 36c37adaea feat: add /claude-supermemory:session command with correct deep link 2026-05-28 15:11:46 -07:00
Robert McLaws a68c51cfb3 Add Swift and Elixir to all ecosystem reference tables
Phase 0 detected Swift (Package.swift) and Elixir (mix.exs) but the
subsequent reference tables had no entries for them, leaving the agent
with no ecosystem-specific guidance after detection.

Adds complete rows for both ecosystems across all four tables:
- Manifest & Config Files
- Entry Points & Architecture
- Conventions & Patterns
- Key Files to Read

Also adds .build, _build, and deps to the skip list for Swift and
Elixir build output folders.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-02-19 15:29:05 -05:00
Robert McLaws 0740bf9120 Make /index command ecosystem-aware with auto-detection
The /index command previously hardcoded JS/TS-specific file names and
entry points, leaving Rust/Python/Go with minimal guidance and
.NET/C#, Java, Ruby, PHP with none at all.

This restructures the command with:
- Phase 0: Auto-detect ecosystem by globbing for manifest files
- Ecosystem Reference table: per-language guidance for manifests,
  entry points, architectural patterns, conventions, and key files
- Coverage for 8 ecosystems: .NET/C#, JS/TS, Rust, Python, Go,
  Java/Kotlin, Ruby, PHP
- Expanded skip list for language-specific build output folders

The single-command UX is preserved (no arguments needed). The agent
detects the stack automatically and uses the reference table to guide
its exploration.

Fixes #32

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-02-19 15:14:52 -05:00
Prasanna721 f8906e6f98 v2: Claude Code Supermemory Refreshed
Refresh plugin architecture with Supermemory

 - Add project-level configuration system (.claude/.supermemory-claude/config.json) for per-repo API keys and container tags
  - Add /project-config command to manage project settings
  - Add /super-save skill for saving project knowledge (architectural decisions, bug fixes, design patterns)
  - Add repo container tag support for team-shared memories (separate from personal memories)
  - Rename prompt-hook to save-project-memory with dedicated repo-level memory saving
  - Remove observation hook (consolidate into other hooks)
  - Enhance context hook, search memory, and summary hook scripts
  - Update supermemory client with repo entity context support
  - Remove MCP config file
2026-02-04 19:14:37 -08:00
Prasanna721 4dc618bf97 Add codebase indexing command
feat: add /claude-supermemory:index command for codebase indexing

Changes:
  - Add /claude-supermemory:index command to explore and index codebase into Supermemory
  - Add add-memory.js script for saving compiled findings
  - Update build.js to include add-memory in build
  - Remove unused settings (maxContextMemories, maxProjectMemories)
  - Update README with new command documentation
2026-01-29 15:20:59 -08:00
Prasanna721 e91b5119a9 Intelligent transcript capture on Stop hook
feat: incremental transcript capture with deduplication

  Points:
  - Remove addMemory from prompt-hook and observation-hook (pass-through only)
  - Capture formatted transcript on Stop hook instead
  - Track last captured UUID per session to avoid duplicates
  - Format: [role:user], [role:assistant], [tool:X], [tool_result:X status]
  - Skip Read tool results, thinking blocks, system reminders
  - Truncate tool results to 500 chars
  - Tracker stored in ~/.supermemory-claude/trackers/{sessionId}.txt
2026-01-29 08:46:43 -08:00