Skip to content

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

Add Semble: natural-language code search primitive that cuts agent tokens by ~98%

ai-booste7cc11efbb9d
diff --git a/README.md b/README.md
index 93003b7..2035d7b 100644
--- a/README.md
+++ b/README.md
@@ -145,6 +145,7 @@ Harness components organized by the problem they solve, not by vendor.
- [codebase-memory-mcp](https://github.com/DeusData/codebase-memory-mcp) — High-performance code intelligence MCP server that full-indexes repositories into a persistent knowledge graph via tree-sitter AST analysis across 66 languages. Replaces dozens of file-read/grep cycles with sub-millisecond structured queries, cutting active tokens by 120× and turning codebase navigation from a context-pressure problem into a pointer-chasing problem. ![Stars](https://img.shields.io/github/stars/DeusData/codebase-memory-mcp?style=flat-square&label=★&color=yellow)
- [Mirage](https://github.com/strukto-ai/mirage) — Mounts S3, Slack, Gmail, GitHub, and Redis side-by-side as a single virtual filesystem so agents interact with every backend through familiar bash commands instead of learning N distinct APIs. The key harness insight: LLMs are already fluent in `grep`, `cat`, and `cp` — leveraging that vocabulary eliminates tool-schema bloat and makes cross-service pipelines compose as naturally as local shell scripts. ![Stars](https://img.shields.io/github/stars/strukto-ai/mirage?style=flat-square&label=★&color=yellow)
- [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)
### Tool Design