Skip to content

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

Add headroom: compress tool outputs/logs/files/RAG before they reach the LLM

ai-boostc1922712fcfd
diff --git a/README.md b/README.md
index e35f7d2..4b789d4 100644
--- a/README.md
+++ b/README.md
@@ -149,6 +149,7 @@ Harness components organized by the problem they solve, not by vendor.
- [dirac](https://github.com/dirac-run/dirac) — Coding agent harness optimized for surgical context curation and API cost reduction: Hash Anchored edits, massively parallel operations, and AST manipulation combine to cut costs 50–80% while improving code quality. Demonstrates that precise context delivery — not just bulk compression — is the right lever for efficient coding agents. ![Stars](https://img.shields.io/github/stars/dirac-run/dirac?style=flat-square&label=★&color=yellow)
- [MinishLab/semble](https://github.com/MinishLab/semble) — Code search primitive that replaces grep+read cycles with natural-language retrieval, cutting active tokens by ~98% while keeping 99% of a transformer-based retriever's accuracy. Ships as an MCP server and CLI, runs on CPU with zero external dependencies — the right drop-in for any coding agent harness struggling with context pressure. ![Stars](https://img.shields.io/github/stars/MinishLab/semble?style=flat-square&label=★&color=yellow)
- [harness-experimental](https://github.com/hoangnb24/harness-experimental) — Repository-level operating harness that turns any software repo into an agent-ready workspace: structured `AGENTS.md`, `HARNESS.md`, and `FEATURE_INTAKE.md` give agents the missing project context — where to start, what the product contract says, how risky the change is, and which decisions future agents should inherit. The most concrete open-source implementation of "coding agents need better repositories, not just better prompts." ![Stars](https://img.shields.io/github/stars/hoangnb24/harness-experimental?style=flat-square&label=★&color=yellow)
+- [headroom](https://github.com/chopratejas/headroom) — Compresses tool outputs, logs, files, and RAG chunks before they enter the context window, cutting active tokens by 60–95% without changing answers. Ships as a library, proxy, and MCP server — the right drop-in layer for any harness where bulky tool returns are the primary context pressure source. ![Stars](https://img.shields.io/github/stars/chopratejas/headroom?style=flat-square&label=★&color=yellow)
### Tool Design