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 OpenSquilla: token-efficient microkernel agent harness with on-device model routing
ai-boost7a8cf3d82bfd
diff --git a/README.md b/README.mdindex d48db07..ea00fee 100644--- a/README.md+++ b/README.md@@ -244,6 +244,7 @@ Harness components organized by the problem they solve, not by vendor.- [PydanticAI](https://github.com/pydantic/pydantic-ai) — Type-safe agent framework where tool definitions, parameters, and return values are Pydantic models. Shifts "agent output doesn't match expected structure" from a runtime bug to a type-check failure; its `RunContext` dependency injection pattern is the reference design for passing session-scoped objects through the harness without global state. - [LangGraph 2.0 Release](https://github.com/langchain-ai/langgraph) — Major 2026 release codifying three years of production orchestration patterns: type-safe streaming, Deploy CLI for managed hosting, and unified agent primitives (Router, Supervisor, Subagent) eliminating the need to hand-roll coordination logic. The persistence layer support for checkpoint-resume recovery is the reference design for resumable multi-day agent tasks. - [OmniRoute: Multi-Provider LLM Gateway](https://github.com/diegosouzapw/OmniRoute) — Intelligent routing across multiple LLM providers with load balancing, intelligent fallbacks, rate limiting, and response caching. Achieves 40–60% token cost reduction through smart model routing (cheap models for simple tasks, capable models for complex reasoning). Essential infrastructure for harnesses operating under strict cost budgets where model selection is a per-turn decision. +- [OpenSquilla](https://github.com/opensquilla/opensquilla) — Token-efficient microkernel agent with an on-device SquillaRouter that dispatches each turn to the cheapest capable model, a unified turn loop across CLI/Web/chat, and persistent memory with on-device embeddings. Demonstrates that harness-level routing and loop optimization — not just model scale — are the binding levers for intelligence density. - [Scaling Managed Agents: Decoupling the Brain from the Hands](https://www.anthropic.com/engineering/managed-agents) — Anthropic's production architecture for separating three stateless components — the "brain" (Claude + harness), "hands" (sandboxes/tools), and "session" (append-only event log) — enabling independent failure and replacement of each. Crash recovery via session replay (`wake(sessionId)` + `getEvents()`) and on-demand container provisioning cut p50 TTFT by ~60% and p95 by over 90%. The reference design for treating agent containers as "cattle not pets" in production.- [Microsoft Agent Framework 1.0](https://devblogs.microsoft.com/agent-framework/microsoft-agent-framework-version-1-0/) — Production-ready 1.0 release (April 2026) unifying Semantic Kernel and AutoGen into a single framework with graph-based orchestration, middleware pipeline for intercepting every execution stage, and declarative YAML agent definitions. DevUI provides a browser-based debugger for visualizing agent execution, message flows, and tool calls in real time. Multi-provider support (Azure OpenAI, Anthropic, Bedrock, Gemini, Ollama) with A2A and MCP integration makes this the most complete enterprise agent harness framework available for .NET and Python.- [Conductor](https://github.com/microsoft/conductor) — Microsoft’s open-source YAML-first CLI for deterministic multi-agent orchestration: Jinja2 routing, static parallel groups, and per-agent model overrides across Claude and Copilot with zero token overhead on the orchestration layer itself. Treats workflows as version-controlled, diffable infrastructure rather than runtime-discovered topology. 