Skip to content

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

Add zerolang: graph-first programming language for agent code manipulation

ai-boostf397d61ed253
diff --git a/README.md b/README.md
index 1a30f13..8feecbe 100644
--- a/README.md
+++ b/README.md
@@ -166,6 +166,7 @@ Harness components organized by the problem they solve, not by vendor.
- [Design Patterns for Deploying AI Agents with Model Context Protocol](https://arxiv.org/abs/2603.13417) — March 2026 field report from an enterprise MCP deployment identifying three protocol-level gaps that break production: missing identity propagation (who is the request for?), absent adaptive tool budgeting, and unstructured error semantics. The concrete mitigation patterns — JWT-enriched tool calls, per-tool timeout contracts, and standardized error-action mappings — are essential before betting on MCP as your primary tool-integration layer.
- [tui-use](https://github.com/onesuper/tui-use) — Expands the agent tool surface beyond non-interactive commands: programmable TUI interaction for REPLs, debuggers, and ncurses apps that standard bash can't reach. A concrete harness primitive for any agent that needs to operate interactive CLI tools without building a custom wrapper per program. ![Stars](https://img.shields.io/github/stars/onesuper/tui-use?style=flat-square&label=★&color=yellow)
- [CLI-Anything](https://github.com/HKUDS/CLI-Anything) — Generates agent-native CLI harnesses for any software, giving agents structured JSON access to applications that were never designed for automation. The CLI-Hub registry and auto-generated SKILL.md files turn tool expansion into a package-manager experience — solving the "long tail" of agent tool coverage without a custom wrapper per program. ![Stars](https://img.shields.io/github/stars/HKUDS/CLI-Anything?style=flat-square&label=★&color=yellow)
+- [zerolang](https://github.com/vercel-labs/zerolang) — Experimental graph-first programming language where agents inspect and edit code through a compiler-derived ProgramGraph (node IDs, graph hashes, types, effects, ownership) instead of fragile text patches. Collapses the typical agent loop of edit-format-reparse-check-fix into a single compiler-validated semantic operation — a reference design for making code manipulation a structured tool interface rather than a guesswork-driven text transformation. ![Stars](https://img.shields.io/github/stars/vercel-labs/zerolang?style=flat-square&label=★&color=yellow)
### Skills & MCP