affaan-m/ECC
The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.
Repository profile
One plugin. Full token-saving stack for Claude Code, Codex, and more. 70-85% fewer tokens.
Repository updates
Get generated mirkobozzetto/espresso development summaries by email, or follow the weekly and monthly RSS feeds.
Sign in to subscribe by email. RSS feeds are public.
Sign in to subscribeTracked growth, recent movement, and commit velocity from stored repository snapshots.
Latest capture 2026-07-08 03:07
4 captures since 2026-05-29
Stars from baseline +2
All tracked data
Frameworks, package managers, ecosystems, and dependency manifests found during catalog scans.
Scanned 2026-07-08 03:07
package.json
javascript ecosystem,
0 dependencies
src/hooks/package.json
javascript ecosystem,
0 dependencies
Searchable topics, generated tags, and stack labels that explain where this repository fits.
Agent instructions and tool configuration paths found in the repository tree.
AI agent config detected
Key config paths
Nearest indexed repositories by embedding similarity.
The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.
Surface AI blindspots before you ship. Put up to 8 AI models on every research, design or coding task.
Give Claude Code, Cursor, Codex CLI a ChatGPT for your codebase. Multi-agent knowledge engine, grounded Q&A with file paths and line numbers. Works in any AI IDE.
Turn every AI agent session into company intelligence. Nex silently unifies every AI agent conversation with your email, Slack, CRM, and 100+ tools into one knowledge graph. The more your team works, the smarter every agent gets.
The harness layer for Claude Code — a reference implementation of harness engineering with hook-enforced dual review, state-machine gates that survive context compaction, and fail-closed safety where it counts. Quality gates that AI can't skip.
The MCP server that turns Claude into the only coding agent hitting 100% on a real benchmark. -77% active tokens, -76% wall time, 0 losses across 96 tasks on Claude Opus 4.7. Structural code navigation + persistent memory. Works with every MCP client.