37 packages found
claude-code-token-optimization
A Systematic Analysis and Discussion of Claude Code for Designing Today's and Future AI Agent Systems
Your portable AI memory — preferences, decisions, and corrections that follow you across models, tools, and devices. Zer
Zero context compaction for Claude Code & LLM agents. Persistent memory powered by OS primitives (demand paging, kswapd
Production-extracted architecture for Claude Code CLI. 3-layer system: CLAUDE.md constitution + specialist Skills + pers
The harness layer for Claude Code — a reference implementation of harness engineering with hook-enforced dual review, st
From a goal to a task DAG, automatically. TypeScript-native multi-agent orchestration.
Opinionated defaults, documentation, and workflows for Claude Code at Trail of Bits
Ask the oracle when you're stuck. Invoke GPT-5 Pro with a custom context and files.
A toolkit that makes Claude Code better at engineering — session memory, dependency analysis, large file navigation, 18
Turn Claude Code into a coordinated team of 40+ specialized AI agents that work together like a world-class engineering
All-in-one agent harness for OpenAI Codex CLI — Boss meta-orchestrator, 400+ agents, 200+ skills, 3 MCP servers. Install
Lossless context compression plugin for Claude Code & OpenCode.
@faugustdevStructured context management framework for LLM agents. Implements Git-like operations (COMMIT, BRANCH, MERGE) to manage
MCP server for persistent context management in AI coding assistants
Code Intelligence: Token-budgeted codebase context for Elixir agents. Solves context window limitations by providing a d
Working memory for Claude Code - persistent context and multi-instance coordination
Skill, agent, MCP, and harness recommendations for Claude Code/custom LLMs: 102,928-node LLM-wiki graph, 91,464 skills,
Cross-session context for Claude Code. CLI + MCP server + /story skill that tracks tickets, issues, handovers, and roadm
@soolaugustZero context compaction for Claude Code & LLM agents. Persistent memory powered by OS primitives (demand paging, kswapd
MCP server for client-encrypted AI agent handoffs with WorkBaton and WorkStash
Context infrastructure for AI-assisted development — on-demand Obsidian vault access via MCP
A personal context store for AI agents and assistants—reuse your existing coding agent CLI (Codex/Claude/OpenCode) with
JSON-driven multi-agent cadence-team development framework with intelligent CLI orchestration (Gemini/Qwen/Codex),
🧠 Session memory lifecycle plugin for Claude Code — structured markdown memory, workstreams, handoff, auto-save hooks
Persistent, local, cross-IDE memory for AI agents — markdown source of truth, LanceDB-powered semantic search, zero clou
One local MCP server that gives Claude, Cline, Codex, and other AI tools the same project memory.
Local, evidence-linked project memory and cited context compiler for coding agents - 98.71% less estimated repeated cont
Deterministic persistent memory for AI agents.
Parks the Claude Code skills you're not using and fetches them the moment you need them — mid-session, per prompt, no re
Human-in-the-loop context compaction for Claude Code — you pick which conversation turns survive, a SessionStart hook re
MCP server gateway for Claude Code, Claude Desktop, and Cline. Loads only specific tools from your MCPs as you need them
ContextLattice is the local-first control plane for long-horizon agent memory and coordination.
Local persistent memory store for LLM applications including continue.dev, cursor, claude desktop, github copilot, codex
Multi-provider AI coding assistant & agent session monitor for VS Code and the terminal — inline completions, code tra
Open-source cognitive coprocessor with active memory for AI agents — persistent recall, semantic search, overnight dream
MCP server giving LLM agents a seven-verb API over papers, documents, code, state, patents, and cached web/Wolfram/YouTu