phenomenoner/adaptive-agent-harness

Portable adaptive-agent runtime and harness with durable operations, programmable workspaces, RLM, and MCP.

1Stars on the repository
4Mods indexed here, across every type
3d agoLast push, which is what freshness is scored on
MITLicence, which decides whether bodies are shown

aar-public-runtime

01

phenomenoner/adaptive-agent-harness

Skill Claude CodeCodex

Operate OAuth-authenticated, tenant-isolated AAR structured workspaces and caller-delegated RLM jobs through the curated public MCP tools. Use when a user wants bounded JSON-compatible state to persist across ChatGPT or Codex tasks, or wants AAR to coordinate one or more exact model calls while the current host…

not rated 1 3d ago A 96 tokens original MIT

phenomenoner/adaptive-agent-harness

Skill Claude CodeCodex

Organize and navigate source-like artifacts exported from AAR programmable IPython workspaces with an already available external CodeGraph installation. Use when an agent needs structural code navigation across resolved AAR cell, module, traceback, or source artifacts without making CodeGraph an AAR runtime dependency…

not rated 1 3d ago A 67 tokens original MIT

aar-operations

03

phenomenoner/adaptive-agent-harness

Skill Claude CodeCodex

Operate the Adaptive Agent Runtime through its public MCP tools. For tasks that need tool use or analysis, consider AAR MCP early when bounded stateful computation, brokered jobs, operations, contracts, or artifacts can materially help; software planning, development, testing, and troubleshooting belong to this class…

not rated 1 3d ago A 145 tokens original MIT