Context Compaction

Pre-compaction hooks + a CAS-guarded task pointer that keep Codex agents on-goal across context auto-compaction — no mainline drift, no duplicate work, no conflicting progress in long runs.

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.

General-purpose agent in one static Go binary: console TUI, ACP server for editors, OpenAI-compatible API with embedded web UI, Telegram gateway, cron scheduler, swarm relay, remote mode. Rules, skills, subagents, hooks, MCP, background tasks, long-term memory, context compaction. Any OpenAI-compatible provider, distroless-ready.

The open-source alternative to Paper.design. A multiplayer design canvas where humans and AI agents design together, live. MCP built in.

Context window optimization for AI coding agents. Sandboxes tool output (98% reduction), persists session memory, and enforces routing across 17 platforms via MCP + hooks.

Local streaming reverse proxy between AI coding agents (Claude Code, Cursor, Codex) and model APIs (Anthropic, OpenAI, Gemini, MiniMax). Meters every token + USD cost, compacts bloated context to cut pay-per-token API spend, and runs shadow-eval to prove quality held. ccusage-style metering + live local dashboard.

Stop re-explaining yourself to AI. MARM offers persistent memory, cross-agent context sharing, write queues, swarm-ready presets, and compaction for clean recall. Includes a live web dashboard for managing memories, logs, and sessions. MCP connects over HTTP & STDIO and works with major LLMs like Claude, Codex, Grok, Gemini, and other models.

A branch-aware Codex skill that saves compact project context, relevant skills, blockers, and next actions so you can start a fresh chat and continue work seamlessly—without carrying unnecessary history or wasting tokens.

Low-context multi-agent task delegation for coding agents. Delegate bounded implementation work to OpenCode, Codex, and Claude with compact briefs, safe execution, and structured results.

Persistent local memory for AI coding agents. Preserve decisions and project context across sessions, compaction, and tools.

Persistent file-based planning for AI coding agents and long-running tasks. Crash-proof markdown plans, session recovery after /clear and compaction, per-turn re-injection against context rot, deterministic completion gate. Manus-style. Install from npm, the Claude Code plugin marketplace, or npx skills. Codex, Cursor, OpenCode, 60+ agents.

A local plugin for image-heavy chats in Codex, Claude Code and other agents: earlier images stop going out with every message, and the model fetches the one it needs by its ID, also after compaction.

Find the ghost tokens. Fix them. Survive compaction. Avoid context quality decay.

Use ChatGPT Pro as a native model in the Codex app — with context, compaction, streaming, images, and optional MCP tools.

Zero-config Claude Code setup with enforced task scaffolding, structured memory, persistent context after compaction, plug-in code standards, optional TDD mode, and zero behavior changes for developers.

Drop-in memory harness for AI agents — 3-tier memory, compaction tree, hybrid search. One command to set up. Works with Claude Code and OpenClaw.

Lossless context compression plugin for Claude Code & OpenCode.