Explore
MCP servers and skills: search, filter by where they run, and compare.
sql-benchmarks-dagsterrctruta
LocalSQL Benchmarking Laboratory using Dagster for Orchestration
PythonApache-2.0★ 2Few starsNo key
MCP servers and skills: search, filter by where they run, and compare.
SQL Benchmarking Laboratory using Dagster for Orchestration
PythonApache-2.0★ 2Few starsNo key
AssetOpsBench - Industry 4.0: A unified benchmark and framework for building, orchestrating, and evaluating domain-specific AI agents for Industry 4.0 asset operations and maintenance, with 460+ scena
in the readmeVideo** · 📊 **Kaggle** · 🚀 **Colab** > [!IMPORTANT] > 🎉 **AssetOpsBench is officially accepted at KDD 2026** (Datasets & Benchmarks Track), Jeju, South Korea, alongside our hands-on tutorial *Building Reliable Industrial Agents
OfficialPythonApache-2.0★ 2.4kNo key
Fast and Accurate Code Search for Agents. Uses 99% fewer tokens than grep+read
in the readmeUses ~99% fewer tokens than grep+read Quickstart • CLI • MCP Server • Installation • Benchmarks Semble is a code search library built for agents. It returns the exact
PythonMIT★ 6.2kNo key
Local-first code intelligence graph for MCP and CLI. Builds a persistent map of your codebase so AI coding tools read only what matters, with benchmarked context reductions on reviews and large-repo w
in the readme简体中文 | 日本語 | 한국어 | हिन्दी Usage · Commands · FAQ · Troubleshooting · GitHub Action · Reproducing the benchmarks · Roadmap AI coding tools often re-read large parts of a codebase
PythonMIT★ 32kNo key
Memory and context engine + app that is extremely fast, scalable, and can be run fully locally. The Memory API for the AI era.
in the skill textlayer for AI. **#1 on LongMemEval , LoCoMo , and ConvoMem ** — the three major benchmarks for AI memory. We are a research lab building the engine, plugins and
SkillMIT★ 31kNo key
Hindsight: Agent Memory That Learns
in the skill textHindsight Banner Documentation • Integrations • Cookbook • Benchmarks • Paper • Hindsight Cloud  and **Cypher relationship queries under
SkillMIT★ 47kNo key
A cyber brain for your AI. It never forgets a detail, remembers exactly what you said, and learns how you work over time. Free, local, works with Cursor, Claude Code, Codex, OpenClaw, Hermes and more.
in the readmeagent the right context on every turn. Quick start · How it works · Benchmarks · Compatibility · Technical reference --- ## What it is A local server that speaks the MCP
PythonMIT★ 908No key
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, determi
in the skill textLong-running tasks · First-class hosts Open the Commands, Multi-agent runs, Benchmarks & more section below for the reference · Full install guide ## Quick Install ```bash
SkillMIT★ 27kNo key
Auditable memory layer for AI agents: zero-LLM-call local ingest (~10ms/msg, air-gapped), matches Mem0 on accuracy at ~1000x lower ingest cost, bi-temporal belief-state, MCP server. Honest LoCoMo/Long
in the readmefeatures, wins and failures alike, 2026). PDFs in `papers/` ; result tables in `benchmarks/AUDIT-RESULTS.md` . Most agent-memory tools (like Mem0) call an LLM on **every message
PythonApache-2.0★ 10No key
A Go framework for building production agent systems with graph workflows, tools, memory, A2A, AG-UI, MCP, evaluation, and observability.
in the readmePrompt Caching**: Automatic cost optimization with 90% savings on cached content - **Evaluation & Benchmarks**: Eval sets + metrics to measure quality over time - **Protocol Integration**: AG-UI for
GoApache-2.0★ 1.9kNo key
LeanCTX — Context Gateway for AI Systems. Control what your AI can see. Open-source Engine for context selection, supported controls, and evidence.
in the readmeScenarios · Demo · Benchmarks · Cookbook · Security · Changelog
SkillApache-2.0★ 3.9kNo key
Token-efficient browser MCP server — structured web pages for AI agents, not raw accessibility dumps
in the readmedump (~50,000 characters). When it needs specifics, it asks for them. ### Benchmarks Measured on Charlotte v0.8.0 against Playwright MCP v0.0.79, by characters returned per tool
Node.jsMIT★ 181No key
in the readmeserver ]( **English** | 日本語 **Give your AI assistant real-time LLM/VLM knowledge.** Pricing, benchmarks, and recommendations — updated every hour, not every training cycle. LLMs have knowledge cutoffs
Node.jsMIT★ 2Few starsNo key
Graph memory for AI agents — decisions, context, and session history that survive across every conversation. Works with any LLM.
in the readmeMIT Quick start · See it · Claude Code & MCP · Benchmarks · Architecture · Roadmap Real run: 25-node graph, checkpoint ckpt_21a0959c3ddf
PythonMIT★ 33No key
SkillX: Automatically Constructing Skill Knowledge Bases for Agents
in the skill textweaker base agents and new environments. Across challenging long-horizon, user-interactive benchmarks such as **AppWorld**, **BFCL-v3**, and **τ2-Bench**, SkillX consistently improves both **task
SkillMIT★ 293No key
Create, Evaluate, and Connect AI Skills
in the skill textThe updated **SkillNet report** presents **SkillNet-Gym**, with executable benchmarks for skill construction, retrieval, and composition, and **SkillNet-Fabric**, which routes tasks through a Wiki built
SkillMIT★ 1.4kNo key
High-performance code-intelligence engine for AI agents and IDE, supports 257 languages, multi repositories, based on graph, with access via CLI, MCP Server, and API. AI coding agents teammate - expos
in the readmeacross 19 coding agents. **Up to 50× fewer tokens per response**. Reproducible benchmarks . > 19 AI coding agents (Claude Code, Kiro, Cursor, Windsurf, VS Code / Copilot, Continue.dev
GoApache-2.0★ 1.9kNo key
Open-source infrastructure that turns scattered SKILL.md files into curated, retrieval-ready agent-skill corpora—with retrieval and evaluation tooling included.
in the skill textretains its upstream license. The public 1,000-skill demo, three agent benchmarks, and live SkillHub show the result. ## 🔥 Latest Updates - **2026-09-17 · v0.4.0
SkillApache-2.0★ 686No key
Cut AI context cost without trusting the compressor. Every reduction is reversible, byte-exact recoverable, and carries an auditable receipt. Local-first, works through proxy, MCP, SDK, or agent wrapp
in the readmePolski · Nederlands · ไทย · Svenska · Čeština · Tagalog · Română What is it? · Install · Quickstart · Benchmarks · Questions · Contribute --- ## What is Entroly? (in plain English) Entroly is a local-first
PythonApache-2.0★ 477No key
Local-first persistent agentic memory powered by Recursive Memory Harness (RMH). Open source must win.
in the readmeinfrastructure retrieval that matches and in several cases strongly outperforms incumbents on benchmarks — and you own every byte of your data. Markdown on disk. Wiki-links
Node.jsApache-2.0★ 331No key
Claude Code usage governor: compact professional output, context slimming, tool-output filtering, telemetry, and drift guardrails.
in the skill textCodex CLI · Gemini CLI · Hermes · DeepSeek Quick Start · Multi-Agent · Why Governor · Benchmarks · Commands · Install Governor started as a Claude Code plugin for context hygiene, tool
SkillMIT★ 131No key
Query-aware context compression for LLMs and coding agents. Cut ~65% of input tokens.
in the readmeevidence containment metric — not downstream LLM completion) Get API key · Arena · Install · Benchmarks · Docs vs Headroom · vs RTK · vs LLMLingua --- ## Why it exists Every LLM call
Node.jsMIT★ 138No key
Code research platform for AI agents; find, understand, and prove context across your code and all of GitHub, in a fraction of the tokens. One toolset, MCP or CLI
in the readmemega-repos. --- ## Table of contents - Quick start - Why Octocode - Built for research (benchmarks) - Tools - MCP - CLI - Configuration - Authentication methods - Security - Language support - Skills - Architecture - Documentation - Troubleshooting
SkillMIT★ 950No key
Who stands behind it
