Subject
27 entries
Claude Code
Bookmarks
Episodic Memory: semantic search for Claude Code conversation history
Semantic search over past Claude Code conversations via local embeddings and MCP. Preserves the trade-offs, alternatives, and preferences that live nowhere else.
Claude Code Unpacked: reverse-engineering the agent harness
Deep reverse-engineering of Claude Code's internals — the agent loop, 50+ tools, and multi-agent orchestration. The closest thing to a technical spec for how it actually works.
rses: cross-agent session handoff
rses lets you transfer a full session context — task, git diff, conversation history — between Claude Code, Codex CLI, and OpenCode. Useful when you want to pick up where one agent left off in a completely different tool.
Cog: cognitive architecture for Claude Code
Cog is a cognitive architecture framework for Claude Code from lab.puga.com.br. Limited public documentation available — the name suggests structured reasoning or memory layers on top of the base Claude Code harness.
Claude Code Auto Dream: automated memory consolidation
Auto Dream is Anthropic's memory consolidation feature for Claude Code — a four-phase process that runs after sessions to merge, deduplicate, and prune memory files. Think of it as automated housekeeping that keeps your AI's long-term memory from accumulating contradictions.
Autoresearch Skill: autonomous skill optimization via eval loops
A Claude Code skill that autonomously optimizes other skills by running eval loops — binary scoring, targeted mutation, keep/discard decisions. Andrej Karpathy's training loop methodology applied to prompt engineering.
Running local LLMs with Claude Code via Unsloth
How to run local LLMs with Claude Code via llama.cpp and Unsloth's GGUF models. The critical fix: Claude Code added an attribution header that breaks KV cache and causes 90% slower inference — must be disabled in settings.json.
Arize AX CLI: LLM observability for AI coding agents
Arize AX CLI makes LLM traces, spans, and experiments machine-readable so AI coding agents can run the same observability analysis as the browser UI. Closes the loop between observability data and the agents that produced it.
Context Mode: MCP server for context window preservation
Context Mode is an MCP server that intercepts large tool outputs and keeps them out of the context window — 98% token reduction, with BM25-indexed session history for continuity after compression. Addresses the 40%-context-consumed-in-30-minutes problem.
visual-explainer: HTML pages instead of ASCII art from agents
visual-explainer is a Claude Code agent skill that generates styled HTML pages instead of ASCII art for diagrams, diff reviews, architecture overviews, and data tables. Fixes the terminal readability problem for complex agent output.
AI Design Components: 76 Claude skills across full-stack development
76 production-ready Claude skills across frontend, backend, DevOps, security, cloud, and AI/ML — organized as 19 plugin groups with a Skillchain v3.0 guided workflow system. One of the larger open-source Claude skill collections.
LLM Council: multi-model deliberation as a Claude Code plugin
LLM Council is a Claude Code plugin that runs a 3-phase multi-model deliberation on any query: parallel responses, cross-model ranking, chairman synthesis. Built by DAIR.AI on Fireworks AI inference.
roro: workspace manager for parallel AI coding agents
roro is a workspace manager for multiple parallel AI coding agents — Agent Calendar for scheduling overnight work, real-time activity monitoring via Claude Code hooks, and personalized agent identities per workspace.
The Companion: web UI for Claude Code and Codex
The Companion is a web UI for Claude Code and Codex sessions — parallel agents, full tool call timeline, permission gating, and session recovery. Replaces terminal tab management for multi-agent workflows.
Searchable Agent Memory in a Single File
A single-file BM25 MCP server that gives a Claude Code agent searchable access to its own conversation history. Shows how much mileage you can extract from a minimal implementation.
Destructive Command Guard (dcg): hook for blocking dangerous agent commands
Destructive Command Guard (dcg) is a sub-millisecond hook that intercepts dangerous commands before AI agents execute them — git resets, rm -rf, DROP TABLE, kubectl deletes. 49+ security packs, SIMD-accelerated, never false-blocks.
Context Lens: see what's filling your context window
Context Lens is a local LLM API proxy that shows what's filling your context window — system prompts vs. tool definitions vs. conversation history vs. tool results. Answers the question every developer asks: why is this session so expensive?
Claude Code Templates (aitmpl.com): marketplace for Claude Code components
Claude Code Templates is a CLI tool and marketplace (aitmpl.com) for installing agents, commands, hooks, MCPs, and settings into Claude Code. 100+ pre-built components installable with a single npx command.
Claude Code: connecting to local models when quota runs out
A practical guide to routing Claude Code to a local LLM when Anthropic quota runs out — using Ollama or similar tools as a fallback so work doesn't stop mid-session. Cheap-plan users will relate.
Claude Code Community
Claude Code Community is a developer community focused on building with Claude Code. A gathering point for practitioners pushing the tool's limits.
Claude Interactive Documentation Workflow: markdown before code
A structured interview-to-implementation workflow using Claude Code: document first, then code. The methodology produces specs that keep LLMs guardrailed and documentation that doesn't require clarifying questions.
claude-supermemory: real-time learning for Claude Code
claude-supermemory connects Claude Code to Supermemory so the agent learns in real-time — preferences, patterns, and project context accumulate across sessions. The memory grows alongside the developer's work.
Claude Code Performance Tracker: daily SWE-Bench monitoring
MarginLab's Claude Code Performance Tracker monitors daily SWE-Bench-Pro scores with statistical significance testing to detect degradation. Answers whether Claude Code's coding performance is consistent over time.
claude-sneakpeek: unlock feature-flagged Claude Code capabilities
claude-sneakpeek installs a feature-flagged parallel build of Claude Code that unlocks swarm mode, delegate mode, and team coordination — capabilities built into Claude Code but not yet publicly released.
Retain: unified AI conversation knowledge base for macOS
Retain is a native macOS app that aggregates AI conversations from Claude Code, Cursor, ChatGPT, and others into a unified searchable knowledge base, then exports learnings to CLAUDE.md so Claude remembers your preferences.
CCPM: Spec-Driven Project Management for Claude Code
CCPM is an agent skill that orchestrates spec-driven software development using GitHub Issues as project state and git worktrees for parallel agent execution, reducing wall time 5x by running independent tasks simultaneously. The anti-vibe-coding project manager.
Terragon Labs: Background Agents for Claude Code
Terragon Labs runs Claude Code agents in parallel inside remote sandboxes, letting you automate multiple development tasks concurrently without managing infrastructure. It's a managed background-agent platform for Claude Code.