Results for “compaction”

Local-first Model Context Protocol (MCP) memory layer for Codex CLI/Desktop, Claude Code, Gemini CLI, Qwen/DeepSeek/Olla

Local-first personal agentic OS and everything app for coding, knowledge work, web design, automations, and artifacts.

NEXO Brain — Shared brain for AI agents. Persistent memory, semantic RAG, natural forgetting, metacognitive guard, trust

@soolaugust

Zero context compaction for Claude Code & LLM agents. Persistent memory powered by OS primitives (demand paging, kswapd

AINL helps turn AI from "a smart conversation" into "a structured worker." It is designed for teams building AI workflo

Local-only observability for AI agents on your machine. One timeline across coding and non-coding agents.

MCP server giving AI coding agents offline, token-efficient persistent memory — recall decisions, patterns, and bugs acr

Open-source self-hosted AI agent runtime and multi-agent framework for autonomous agent swarms. Agent memory, MCP tools,

CI for ink stories — compile checks, exhaustive branch playtesting, dead-content detection. MCP server + CLI.

The Mind Palace for AI Agents - HIPAA-hardened Cognitive Architecture with on-device LLM (prism-coder:7b), Hebbian learn

The MCP server that turns Claude into the only coding agent hitting 100% on a real benchmark. -77% active tokens, -76% w

Session continuity for AI coding agents — your agent picks up where it left off. Persistent memory for Claude Code, Open

Zero context compaction for Claude Code & LLM agents. Persistent memory powered by OS primitives (demand paging, kswapd

MCP server for spreadsheet analysis and editing. Slim, token-efficient tool surface designed for LLM agents.

Persistent memory MCP server for AI agents — Rust, 19 tools, knowledge graph, Hebbian learning, episodic memory, contrad

Lightweight Long-Term Memory for LLM Agents.

MCP that allows you to use top-tier LLM's, such as GPT-5.6 and Fable 5, in any IDE via Notion provider

Apple-native execution layer for AI coding agents: compile, validate, repair, and prove Swift surfaces.

Standalone enforcement system for indexed rules, validators, Codex skills, MCP, hooks, and CI adapters.

ARIS ⚔️ (Auto-Research-In-Sleep) — Lightweight Markdown-only skills for autonomous ML research: cross-model review loops

A production-ready MCP server that builds a world model for codebases, preventing hallucinations, repeated mistakes, and

Open-source cognitive coprocessor with active memory for AI agents — persistent recall, semantic search, overnight dream

GoPeak — The most comprehensive MCP server for Godot Engine. 95+ tools: scene management, GDScript LSP, DAP debugger, sc

Todo and task management

acrawl — LLM-powered web crawler. Describe what you want in plain English, get structured data back. Single Rust binary,

Durable MCP control plane for long-running Codex Desktop tasks

Zero-key MCP web search for AI agents: native Chinese sources, multi-engine aggregation, optional commercial backends, n

Persistent, searchable context storage across Claude Code sessions using SQLite + FTS5

🦫 Privacy-first virtualization layer for LLM context with MCP protocol for tool access.

Local MCP broker that exposes one compact MCP entry for MCP clients while routing to many configured upstream servers.

Persistent memory for any AI — MCP server, HTTP API, CLI. Works with Claude, ChatGPT, Grok, Gemini, Codex, Cursor, OpenC

CLI-first API testing tool. YAML-defined tests, structured JSON output, built for AI-assisted workflows.

Compact Rust agent CLI for local OpenAI-compatible models, with Docker isolation, sessions, skills, MCP, plan mode, sub-

CLI and MCP server that reads Tokens Studio applied tokens from a Figma URL. Compact tree, grouped dictionary, or Figma-

Token-efficient browser automation MCP for AI agents, with semantic page snapshots and stable element IDs.

Local-first, AST-aware context compiler that sits between Claude Code and the filesystem as an MCP server. Built for Cla

MCP server for testing Business Central and MobileNAV through real browser and Android clients

Project workspace management and registry CLI for AI agent development

TokToken is a fast, single-binary C codebase indexer for AI coding agents. Powered by universal-ctags and SQLite FTS5, i

claude-session-continuity-mcp

o9k — token-efficiency meta-framework for AI coding agents (Claude Code, Cursor, Codex, OpenCode, Hermes): seven pillars

A MCP server for datetime formatting and file name generation.

The leading, most token-efficient MCP server for GitHub source code exploration via tree-sitter AST parsing

Your AI forgets everything between sessions. Rekindle fixes that.

Token-saving code search for AI coding agents — TypeScript, JavaScript & Python (zero setup), C#, C++, Go & 30+ more, vi