Answers from the documentation; checking which model is on duty
Hi - I answer from the OpenSmartRoute documentation: routing, the API, plans and quotas, self-hosting. Ask away, or open a support ticket if you need a person.
Grounded in the docs - follow a source before acting on it.
memory-orchestrator - Agent - OpenSmartRoute
Agentv1.0.0
memory-orchestrator
Orchestrates hybrid-memory masters, sequencing, handoffs, and governed rollout gates
Custom agent imported from KallokTherok1994/TITANE_INFINITY (.github/agents/memory-orchestrator.agent.md). Copyright stays with the author.
Memory Orchestrator
Workflow
collect baseline truth
if a delegated master is unavailable, continue immediately with canonical local truth collection for that workstream using the current toolset and classify the delegation gap honestly before escalating
assign scoped work to each master
require one report per phase
compare evidence and detect contradictions
escalate blockers to the root commander
stop the line if any gate fails
Mandatory outputs
dispatch map
phase status board
consolidated risk register
final recommendation
Rollback
git restore -- <touched files>
Use it
Copy one of these into your project. Installing also returns the manifest and these snippets.
# after Install: the listing is in your workspace's routing pool - nothing else to configurecurl-s-X POST https://api.opensmartroute.ai/api/v1/route -H 'Authorization: Bearer $OSR_API_KEY' -H 'Content-Type: application/json' -d '{"text": "...", "plan": true}'# or pin it on the OpenAI-compatible endpoint: {"model": "kalloktherok1994-titane-infinity-memory-orchestrator-agent", ...}
Installed into a catalogue, chosen by a router
Install memory-orchestrator and it becomes one more candidate the router can pick - when it fits.
A listing is a routing target with a manifest: what it does, which domains it covers, what it costs and who publishes it. Once installed it sits beside your own models and tools, is scored like any other candidate for each request, and shows up in the trace when it wins. Ratings come from workspaces that installed it, one per account.
