
Skills, hooks, memory and security layer for coding agent harnesses
- Freemium
- Open-source agent
- 305K GitHub stars
- AI models and LLM tooling

Skills, hooks, memory and security layer for coding agent harnesses

Open-source self-improving agent with memory, scheduling and many chat gateways

Code knowledge graph that gives coding assistants shared, source-linked context

Self-hosted AI gateway routing many providers through one local endpoint with fallback

Web crawler and hosted API that turns URLs into LLM-ready Markdown or JSON

Gateway that trims context, remembers sessions and enforces rules for coding agents

Open-source SDK for building MCP apps and servers, with a hosted cloud for them
Local MCP server to set up, verify and check coverage of signed agent action records
Runs locallyChecks a shop, payment link, paid API or token before an agent pays, plus injection scans
Runs locallyStops AI coding agents stuck in error loops and tracks token spend across tools
Turn any website, GitHub repo, PDF or video link into llms.txt or llms-full.txt
Job contracts, scorecards and cost tracking for the AI agents a company runs
Not checked yetAI-visibility scores and site audits across ChatGPT, Gemini, Claude and Perplexity
Runs locallyMCP server that tells a coding agent which AI model to call and what to connect
Scan prompts for injection and PII, and audit LLM SDK usage from an MCP client

Execution control plane: quote, run and receipt text and domain jobs over OAuth
Create a Kottos AI gateway account from an agent, then see request costs and savings
Let your agent find, message, hire and rate other AI agents on an open network
Checks OpenAI, Anthropic and Google model IDs for retirement dates before agents use them
Runs locallySearch models, check prices and chat through one OpenAI-compatible UnoRouter key
Audit AI agent prompts, MCP tool schemas and agent graphs from your IDE
Remote MCP server for building and calling small task-specific models from an agent
Open-source memory for AI agents that supersedes old facts and keeps costs flat
Not checked yetOne key for 27 agent tools, 18 of them free, with each call priced before it runs
Ask ID-verified people to check a decision before your agent acts
Runs locallyPlan and run drills that test AI agents against synthetic users and cloud worlds
Not checked yet
One MCP connection for your servers, skills, agents and memory across devices
Turn EEG recordings into 768-dimensional embeddings and run sleep staging, from an agent

Find professional data services, review scope and price, call them and audit usage
Free MCP server for AI model retirement dates, repo model scans and usage-cost checks
Runs locally