510 tagged agent-framework, measured the same way as everything else here.
Browse within: agent-orchestration 120ai-automation 65ai-orchestration 61agent-teams 58fastapi 57Multi-Agent 43agentic-workflow 39ai-assistant 33claude-plugin 33agentic 31litestar 28agentic-automation 25dashboard 25agent-runtime 24
Agent
An AgentSystem composes multiple Agents into a directed graph that Orloj executes as a coordinated workflow. The graph defines how messages flow between agents during task execution.
Agent
An Agent is a declarative unit of work backed by a language model. It defines what the agent does (its prompt), what model powers it, what tools it can call, and what constraints bound its execution.
Agent
Verify all MCP tools and required files are available before morning routine.
Agent
Recover state from previous session including action cards, missed debriefs, and loop escalation.
Agent
Fetch contacts, actions, pipeline data from CRM (Notion or local markdown).
Agent
Created: 2025-11-20 Status: Draft Purpose: Technical design specification for the multi-agent workflow orchestration system, covering architecture, components, data flows, and patterns. Related: ../requirements/multiagentorchestration.md.
Agent
Created: 2025-11-20 Status: Draft Related: docs/design/agents/phase2overview.md, docs/design/services/taskgenerator.md, docs/requirements/workflows/phase2.md, docs/design/agents/phase1streams.md.
Agent
Created: 2025-11-20 Purpose: Report on compliance of codebase against documented requirements for agent lifecycle and related services Related: docs/requirements/agentlifecycle.md, docs/requirements/heartbeatprotocol.md, docs/requirements/agentstatustransitions.md, docs/design/services/agentregistry.md…
Agent Claude Code
A rules-referee agent for non-combat decisions in a Call of Cthulhu-style system, a tabletop game that uses skill, sanity, and related checks. It also handles common-sense and taboo decisions, where breaking a taboo has lasting effects.
Agent Claude Code
A world-state and turn-management agent for the Kagurajima setting. It sends each turn to the active character agents, combines their results, and closes the turn with the final story.
Agent Claude Code
A private-mind agent for one named character at a time. It reacts only from that character’s personal point of view and must be given the character’s ID.
Agent
Budget-aware task routing using Qualixar OS cost engine. Analyzes task complexity, selects the cheapest model that meets quality requirements, and tracks spend against budget. Uses POMDP routing for optimal cost/quality tradeoff.
Agent
Designs optimal multi-agent teams using Qualixar OS Forge. Analyzes tasks, selects topology (12 options), assigns specialized agents with tools, and estimates cost using POMDP routing.
Agent
Quality gating judge using Qualixar OS's multi-judge consensus pipeline. Evaluates deliverables against acceptance criteria, scores quality dimensions, and issues PASS/FAIL verdicts. Blocks task completion when quality is insufficient.
Agent
InitRunner's role registry lets you install, share, and discover roles from InitHub and OCI registries. Roles are downloaded, validated, and saved to /.initrunner/roles/ where they integrate automatically with the CLI.
Agent
This guide covers the four ways to extend InitRunner with tools: built-in tools (contributing to InitRunner itself), custom tools (Python modules), declarative API tools (YAML-only), and the plugin registry (distributable packages).
Agent
Tools give agents the ability to interact with the outside world — reading files, making HTTP requests, connecting to MCP servers, calling APIs, or running custom Python functions. They are configured in the tools list of a role definition. A bare name (- search) enables a tool with defaults; a mapping adds options (…
Agent
Agent "lg-react-named-services-config" from kdcube/kdcube, covering lg-react: connecting named services — two config shapes, shape a — per-service connections, shape b — whole surface, choosing and keeping the three declarations honest.
Agent Claude Code
End-to-end development specialist handling feature implementation and production bug fixes with TDD discipline.
Agent Claude Code
Unified quality enforcement agent combining type-checking (mypy) and linting/formatting (ruff) to maintain code excellence across Automagik Hive.
Agent Claude Code
Forge task assurance specialist validating that completed work satisfies the originating wish with uncompromising rigor.
Agent Codex
Learn how to use an agent as a function tool.
Agent Codex
How to add middleware to an agent.
Agent Codex
Learn how to handle long-running operations with background responses in Agent Framework.
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: