Skip to content

Awesome list for AI agent harness engineering: tools, patterns, evals, memory, MCP, permissions, observability, and orchestration.

Merge pull request #367

Adrian Vale2917aaecff5b
diff --cc README.md
index 3b30c41,c5bbde0..c6d7e19
--- a/README.md
+++ b/README.md
@@@ -584,8 -583,9 +584,10 @@@ Real repositories worth studying — ea
- [Trustworthy agents in practice](https://www.anthropic.com/research/trustworthy-agents) — Anthropic's April 2026 framework for governing autonomous agents through five principles: human control, value alignment, secure interactions, transparency, and privacy. The most complete published treatment of how to design harness-level governance that keeps pace with increasing agent capability and autonomy.
- [RAMPART](https://github.com/microsoft/RAMPART) — Pytest-native safety and security testing framework for agentic AI that turns red-team findings into repeatable CI tests. Supports statistical trials (e.g., "safe in 95% of runs") rather than single-shot pass/fail, making it the first concrete tool for treating agent safety as an engineering discipline rather than a post-hoc audit. ![Stars](https://img.shields.io/github/stars/microsoft/RAMPART?style=flat-square&label=★&color=yellow)
- [aiming-lab/AutoHarness](https://github.com/aiming-lab/AutoHarness) — Open-source Python governance harness that wraps any OpenAI-compatible client with a configurable tool-approval pipeline, prompt-injection defense, secret-exposure checks, and JSONL audit trails. Demonstrates how to productize "Agent = Model + Harness" into a drop-in governance layer rather than scattering guardrails across application code. ![Stars](https://img.shields.io/github/stars/aiming-lab/AutoHarness?style=flat-square&label=★&color=yellow)
+- [Speakeasy control plane](https://github.com/speakeasy-api/gram) — MCP gateway that scopes agent tool access by identity, team, and role, with security policy enforced on each action and an audit trail. Useful as a reference for putting authorization at the tool boundary instead of relying on model prompts to restrict access.
+ - [MCP Security Testing Checklist](https://loki-intelligence.com/blog/mcp-security-testing-checklist) — Twelve-step practitioner verification checklist for MCP server and tool-harness boundaries: OAuth/token scoping, schema and description poisoning, dynamic discovery freezes, SSRF/path-traversal argument validation, cross-tenant isolation, and secret redaction in tool responses. Provides a concrete pre-release audit rubric for verifying that MCP integrations cannot be abused to cross harness trust boundaries.
+
---
## Evals & Verification