Skip to content

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

Add mindwalk to Debugging & Developer Experience section

Adrian Vale5b0d798afbcb
diff --git a/README.md b/README.md
index 1a4be79..508bee9 100644
--- a/README.md
+++ b/README.md
@@ -354,6 +354,7 @@ Harness components organized by the problem they solve, not by vendor.
- [Characterizing Faults in Agentic AI](https://arxiv.org/abs/2603.06847) — March 2026 empirical study mining 375 GitHub issues across real-world agent systems (AutoGen, CrewAI, OpenAI Agents SDK, LangChain, CAMEL, DB-GPT) to build the first grounded taxonomy of agent-specific faults: initialization failures, role deviation, memory/state deficiencies, orchestration failures, and tool integration errors. Provides architecture-level fault classification that harness engineers can use as a systematic debugging checklist.
- [More Visibility into Copilot Coding Agent Sessions](https://github.blog/changelog/2026-03-19-more-visibility-into-copilot-coding-agent-sessions/) — GitHub's March 19, 2026 changelog is short but materially useful: setup-step logs, collapsed subagent traces, and clearer session-stage visibility are exactly the kind of DX improvements that make long-running agent failures debuggable in practice. It is a concrete reminder that trace readability is part of the harness, not an afterthought layered on top.
- [AgentStepper: Interactive Debugging of Software Development Agents](https://arxiv.org/abs/2602.06593) — February 2026 interactive debugger for agent execution trajectories that organizes raw logs into structured, side-by-side conversations (agent↔LLM and agent↔tools). Enables step-through execution, breakpoint manipulation, and mid-trajectory inspection. Developer study shows frustration scores drop from 5.4 to 2.4 (NASA TLX) and comprehension accuracy improves significantly — the first concrete evidence that interactive debugging primitives materially reduce the cognitive load of understanding multi-turn agent behavior.
+- [mindwalk](https://github.com/cosmtrek/mindwalk) — Replays Claude Code and Codex sessions on a 3D map of your codebase, turning raw JSONL logs into a spatial view of where the agent searched, read, and edited. The glow-based visualization makes exploration drift and context pressure immediately visible — a concrete debugging primitive for reviewing whether an agent's footprint matched the intended task scope. ![Stars](https://img.shields.io/github/stars/cosmtrek/mindwalk?style=flat-square&label=★&color=yellow)
### Human-in-the-Loop