RAM supports OpenCode transcript indexing and MCP server integration.
- OpenCode installed and configured
- RAM installed (
cargo install ramemor from source)
ram setupThis single command:
- Indexes your existing OpenCode transcripts
- Writes the MCP server entry to
~/.config/opencode/opencode.json - Verifies the configuration
Then restart OpenCode to activate.
Add to ~/.config/opencode/opencode.json (or opencode.json in your project root):
{
"mcp": {
"ramem": {
"type": "local",
"command": ["/usr/local/bin/ram", "serve"],
"enabled": true
}
}
}Use which ram to find the correct path.
OpenCode transcripts are expected to follow a JSONL format similar to Claude Code. The parser extracts:
- User messages
- Assistant responses
- Tool calls and results
- Session metadata (timestamp, project context)
# Check status
ram status
# Search indexed content
ram search "opencode"
# View recent memories
ram search "" --limit 10 --output json# Start indexing with watcher
ram index --watch
# In another terminal, work with OpenCode
# ...
# Search for context
ram search "how did we implement X"
# Memorize important decisions
ram memorize "Decision: Use pattern X for Y" --tags decisionSince MCP integration may not be available, use these CLI commands:
ram search "query" [--limit N] [--scope S] [--output json|text]ram memorize "content" --tags tag1,tag2 [--importance 0.8]ram status [--output json|text]ram index [--path /custom/path] [--watch]RAM configuration file: ~/.config/ram/config.toml
[embedding]
backend = "fastembed"
model = "AllMiniLML6V2"
[search]
rrf_k = 60
decay_half_life_days = 7.0
[index]
transcript_paths = [
"~/.opencode/transcripts", # Add OpenCode path
"~/.claude/projects"
]OpenCode transcript locations (check OpenCode docs for current paths):
~/.opencode/transcripts/ # Typical location
~/.config/opencode/sessions/ # Alternative location
Use ram config show to see configured paths.
- Check OpenCode transcript location in OpenCode settings
- Add custom path:
ram config set index.transcript_paths '["/your/path"]' - Verify files exist:
ls -la /path/to/transcripts - Re-index:
ram init --force
- Check transcript format matches expected JSONL structure
- View parser logs:
ram index --path /path/to/transcript --verbose - Report format issues on GitHub with sample transcript (redacted)
- Verify indexing completed:
ram status - Check chunk count is non-zero
- Try broad query:
ram search "" - Check scope filter:
ram search "query" --scope global
- MCP support: Depends on OpenCode's MCP implementation status
- Hooks: No automatic session hooks without MCP integration
- Real-time indexing: Requires manual
--watchflag or periodic re-indexing
# Terminal 1: Start watcher
ram index --watch
# Terminal 2: Work with OpenCode
# ... coding session ...
# Terminal 3: Search context
ram search "how did we handle errors"
# Memorize important decisions
ram memorize "Convention: Use error type X for Y" --tags convention,error-handling
# Check what's indexed
ram statusIf OpenCode adds MCP support, RAM will provide these tools:
search_memory- Hybrid searchmemorize- Explicit memory storageforget_memory- Remove memoriesget_memory- Retrieve by IDlist_recent_memories- Recent entriesupdate_memory- Update tags/importancememory_status- Database stats
Check RAM releases for updates on OpenCode MCP integration.
- Read the FAQ for common questions
- See Architecture for how RAM works internally
- Check Troubleshooting for more solutions
- Monitor OpenCode GitHub for MCP support updates