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 LangChain Connections (managed credentials, per-caller identity) to Permissions & Authorization
ai-boostfa3275de3db6
diff --git a/README.md b/README.mdindex 99512a8..62ec878 100644--- a/README.md+++ b/README.md@@ -255,6 +255,7 @@ Harness components organized by the problem they solve, not by vendor.- [Aegis](https://github.com/Justin0504/Aegis) — Pre-execution firewall that intercepts, classifies, and blocks agent tool calls before they execute, with a compliance cockpit for real-time monitoring, human-in-the-loop approvals, and a tamper-evident audit trail. The zero-code-change integration makes runtime policy enforcement practical for existing agent deployments. - [When "Do Not" Is Not Deny: Security Rules in CLAUDE.md vs Built-In Controls](https://arxiv.org/abs/2608.23550) — Analyzes 481 public CLAUDE.md files and finds only ~4% of natural-language security rules are backed by a matching built-in control, exposing the gap between documented intent and enforced permissions. A concrete reminder that harness instructions are not guardrails unless they map to deterministic enforcement.- [Do User-Authored Permission Policies Improve Protection Against AI Agent Overreach?](https://arxiv.org/abs/2608.27443) — August 2026 user study (113 non-technical participants) comparing per-action HITL approval, automated model review, and user-authored allow/ask/never rules. The key harness finding: pre-authored policies blocked ~20 percentage points *less* overreach than per-action approval — users overwhelmingly set "ask" as their rule and then approve anyway, so static rule pre-commitment degenerates back into runtime prompts without gaining protection. Essential evidence that permission UX design (not just policy expressiveness) determines whether stated intent survives contact with real agent actions.+- [Connections: Managed Credentials and Per-Caller Identity for Managed Deep Agents](https://www.langchain.com/blog/connections-managed-credentials-and-per-caller-identity-for-managed-deep-agents) — LangChain's September 2026 implementation of on-behalf-of authorization as a harness primitive: credentials live in the workspace (never in `.env` or the build) and are resolved at run time by slug, with user-owned connections resolving per caller so agent actions carry the requesting human's identity rather than a shared service account. The two-axis model (agent-owned vs. user-owned × static secret vs. OAuth grant) is the clearest published pattern for the "who asked?" question that a hard-coded API key structurally cannot answer.### Memory & State