Skip to content

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

Add Organizing Context in a Multi-Agent Harness to Context Delivery & Compaction

ai-boost3be1ff8dde95
diff --git a/README.md b/README.md
index e050884..e31e80d 100644
--- a/README.md
+++ b/README.md
@@ -170,6 +170,7 @@ Harness components organized by the problem they solve, not by vendor.
- [PRO-LONG](https://github.com/alexisfox7/PRO-LONG) — Programmatic memory framework for long-horizon agents: the harness appends all observations to a structured log and lets the agent search it with code instead of relying on fixed summarization or compaction policies. Achieves 4.2–5.8× token reduction and matches or exceeds specialized harnesses on ARC-AGI-3, showing that long-horizon context management can be a programmable retrieval problem rather than a compression problem. ![Stars](https://img.shields.io/github/stars/alexisfox7/PRO-LONG?style=flat-square&label=★&color=yellow)
- [Graft](https://github.com/NanoNets/Graft) — Builds a local, regenerable graph of plain-English system explanations and code relationships, then rides along inside Claude Code, Cursor, Codex, and Gemini via MCP and statusline hooks so the agent stops rediscovering the repo every session. The published SWE-bench Verified and efficiency benchmarks make it the clearest recent demonstration that context delivery for coding agents is a navigation problem, not just a compression problem. ![Stars](https://img.shields.io/github/stars/NanoNets/Graft?style=flat-square&label=★&color=yellow)
- [ktx](https://github.com/Kaelio/ktx) — Self-improving executable context layer for data and analytics agents: it ingests warehouses, BI tools, and wikis to build a semantic layer with approved metrics, joinable columns, and resolved fan/chasm traps, then serves the result to Claude Code, Codex, and Cursor through MCP. Fills the gap where general-purpose agents invent metric logic on every question — it turns warehouse querying from a prompt-guessing problem into a governed, retrievable context problem. ![Stars](https://img.shields.io/github/stars/Kaelio/ktx?style=flat-square&label=★&color=yellow)
+- [Organizing Context in a Multi-Agent Harness](https://www.langchain.com/blog/organizing-context-in-a-multi-agent-harness) — LangChain's September 2026 introduction of context modes for subagents: `isolated` subagents start fresh (context isolation as a firewall), while `forked` subagents inherit the supervisor's full conversation — excised trailing tool call, task description rewritten as a user message, prompt caching preserved by design. The worker-vs-verifier decision rule — fork workers that continue in-progress investigations, isolate verifiers that must judge independently — is the clearest published guidance for a question every multi-agent harness faces but few document: exactly how much context should a subagent receive?
### Tool Design