Awesome list for AI agent harness engineering: tools, patterns, evals, memory, MCP, permissions, observability, and orchestration.
Python agent-harnessagent-memoryagent-orchestrationai-agent-harnessai-agentsawesome-listcontext-engineeringharness-engineeringmcp
Add Codex as a Platform to Task Runners & Orchestration
ai-boostca71915edfa6
diff --git a/README.md b/README.mdindex 049b6c0..fd25e8b 100644--- a/README.md+++ b/README.md@@ -292,6 +292,7 @@ Harness components organized by the problem they solve, not by vendor.- [LangGraph](https://github.com/langchain-ai/langgraph) — Graph-based state machine framework for multi-agent harnesses: models supervisor/subagent topologies, error-recovery branches, and checkpoint persistence as first-class primitives. The most widely adopted harness orchestration layer in production. - [OpenAI Agents SDK](https://github.com/openai/openai-agents-python) — Lightweight multi-agent framework built around handoffs and guardrails; the production successor to Swarm. Complements LangGraph for harnesses where delegation patterns are simpler than full graph orchestration. - [Codex SDK](https://developers.openai.com/codex/sdk) — OpenAI's official SDK for programmatically controlling local Codex agents from TypeScript or Python: start threads, run prompts, resume sessions, and choose sandbox presets (read-only, workspace-write, full-access) so Codex can be wired into CI/CD or custom agent surfaces instead of remaining locked inside the CLI.+- [Codex as a platform: build on the open agent harness](https://developers.openai.com/blog/codex-as-a-platform) — OpenAI's September 2026 guide to treating the open-source Codex harness as reusable infrastructure rather than a product to adopt wholesale: your application owns the interface, business context, MCP tools, and approval gates, while the app-server owns the agent loop and sandboxed execution. The clearest first-party articulation of the division of labor every embedded-agent harness must decide — and the ARC-AGI-3 datapoint (retained reasoning + compaction tripled scores while cutting output tokens 6×) is the latest evidence that harness configuration, not model choice, is the performance lever.- [Google ADK](https://github.com/google/adk-python) — Google's code-first agent framework with built-in multi-agent orchestration, tool registration, session state, and eval pipeline. Its `Runner` and `AgentTool` patterns are the reference implementation for wrapping sub-agents as tools in a larger harness. - [strands-agents/harness-sdk](https://github.com/strands-agents/harness-sdk) — AWS's open-source, model-driven agent SDK that treats the loop, tool binding, and guardrails as first-class primitives. Supports Bedrock, Anthropic, OpenAI, Gemini, and Ollama with native MCP, built-in observability, and multi-agent patterns — the missing AWS open-source harness framework alongside Bedrock AgentCore. - [Build Long-running AI agents that pause, resume, and never lose context with ADK](https://developers.googleblog.com/build-long-running-ai-agents-that-pause-resume-and-never-lose-context-with-adk/) — Google's May 2026 guide to production agents that survive days-long idle periods: `DatabaseSessionService` for persistent sessions, webhook-triggered `state_delta` resumption that lets containers scale to zero, and explicit state machines instead of dumping raw JSON into vector databases. Complements Anthropic's managed-agents architecture with a cloud-native deployment perspective.