WhimRead needs JavaScript for on-site search.
Whim
Read
browse at whim
Discover
All tools
Picks
Surprise
About
Search
中文
Agent harnesses
Trail-Code
trailhq/Trail-Code
Shared memory and code-map context layer for Claude Code, Cursor and Codex coding agents.
View on GitHub
Copy link
Topics
ai-agents
claude-code
code-graph
context-engineering
developer-tools
knowledge-graph
llm
mcp
Related projects
Graft
11.2k
A self-learning context layer for coding agents. It builds a tree-sitter code map and saves team learnings, then feeds them to Claude Code, Cursor, Codex, and other agents through hooks and MCP.
everything-claude-code-zh
2k
A Chinese-localized configuration collection based on Everything Claude Code, providing agents, skills, hooks, commands, and rules to enhance Claude Code and other coding agents.
harness-books
3.3k
Harness Books is a two-book series on harness engineering that examines how Claude Code and Codex organize prompts, query loops, context governance, permissions, and verification.
Agent-Cockpit
501
Agent Cockpit is a local whiteboard and MCP server for AI research agents that traces every claim back to the run and code that produced it, with staleness checks and replay.
claude-code-workflow
711
A lightweight reliability layer for Claude Code, Codex and Cursor that installs shared AGENTS.md rules and workflows, emphasizing verification, reversible changes and risk-aware confirmation.
ponytail
195.5k
A coding skill that teaches AI agents minimalist, YAGNI-style implementation with review and audit commands.
11292
ai-agents,claude-code,code-graph
Shared memory and code-map context layer for Claude Code, Cursor and Codex coding agents.
←
Previous
cytoscape.js
Next
→
inkos