MCP servers and skills: search, filter by where they run, and compare.
Budget enforcement and spend tracking for autonomous agents — per-agent limits, threshold alerts, cost analysis. MCP server.
PythonMITFew starsNo key
Terminal-based AI coding agent that can reason, execute tools, browse the web, and modify code in real time. Built from scratch with support for MCP servers, hooks, and persistent sessions for fully e
PythonMIT★ 2Few starsNo key
The AI agent that flies on its own. Two commands to fly. 🪶
PythonMIT★ 2Few starsNo key
PraisonAI 🦞 — Hire a 24/7 AI Workforce. Stop writing boilerplate and start shipping autonomous self-improving agents that research, plan, code, and execute tasks. Deployed in 5 lines of code with bui
PythonMIT★ 9.3kNo key
Deterministic RoastPilot controller: the controller owns the loop, the language model advises, and safety policy validates commands before actuation.
PythonMIT★ 2Few starsNo key
Turn corrections from AI agent logs into guidance for similar tasks. Local memory with semantic retrieval, prompt-context hooks, and response checks.
SkillApache-2.0★ 9No key
🕸️ Crawl any website into a queryable navigation + content graph and find the shortest click-path to any action — deterministic, no-LLM browser automation
PythonMIT★ 5No key
Local-first MCP server that tells coding agents which files to read, and how sure it is. 97% Hit@10 on Java (SWE-bench Multilingual), 89% on Python (SWE-bench Lite), zero LLM cost. mcp-brain calibrate
PythonMIT★ 5No key
Local-first memory infrastructure for coding workflows: deterministic retrieval, explainable traces, MCP/REST/SDK interfaces, and standalone browser-first operation.
PythonApache-2.0★ 1Few starsNo key
Runtime behavioral security for Agentic Skills — deterministic policy engine, human-in-the-loop gate, full OWASP Agentic Skills Top 10 (AST01–AST10) coverage. Not another SKILL.md scanner: traces what
PythonMIT★ 1Few starsNo key
The Agent that evolves through use, distills session experience into domain knowledge, then converts knowledge into executable skills.
SkillMIT★ 9No key
Complete security framework for AI Agents, MCP Servers, and RAG pipelines. Features automated MCP fuzzing, cross-agent poisoning detection, persistent memory audits, unified risk scoring, and CI/CD se
PythonMIT★ 1Few starsNo key
MCP connector that verifies a claim's grounding against reality (quotes, citations, code, repos, math) with no LLM in the verification path. Works in Claude and Gemini.
PythonMIT★ 2Few starsNo key
Audio perception for AI agents: measure, see, compare, edit and synthesize sound over MCP. Loudness, spectrograms, pitch, events, transcription, cleanup.
PythonMITFew starsNo key
MCP server wrapping VirusTotal and urlscan.io as typed tools for Claude-driven threat investigation and IOC pivoting.
PythonMITFew starsNo key
A personal memory layer for your AI tools. Intelligent authoring (gap detection, self-enriching graph, session-synthesis loop) + measurably good retrieval (94.9% blind Cov@10, sub-ms latency). Domain-
PythonMIT★ 2Few starsNo key
Emotional memory for AI agents — dual-engine mood tracking, behavioral prediction, and governed memory that fades naturally over time. MCP server with 12 tools. Built with Opus 4.6.
PythonMIT★ 1Few starsNo key
Terminal-native, MCP-native trading-strategy backtester an AI agent can drive — with built-in overfitting guards (walk-forward, deflated Sharpe, costs).
PythonMIT★ 1Few starsNo key
PDF word-level confidence extraction skill with OCR modality detection, bounding box mapping, Gemini 3.7 Flash context-aware auto-correction, and interactive review dashboard.
SkillApache-2.0Few starsNo key
MCP server for content-aware landscape → vertical (9:16) video reframing. Analyse, preview, then render — entirely local.
PythonApache-2.0Few starsNo key
Fraud Prevention MCP server using FraudLabs Pro API.
PythonMITFew starsNeeds a key
Who stands behind it
