Autonomous AI agents that perform tasks independently
Causality tracing for multi-agent AI systems: find the node that broke the chain.
sergeyizmailov
Deterministic security tests for unsafe multi-agent handoffs and authority escalation
LangChain and CrewAI tools for Sirenic - official French & European company data, paid per call via x402 (USDC/EURC on Base). No account, no API key.
...moreRekreate Digital
Injection-hardened, storage-agnostic, private memory layer for AI agents.
eyas-ranjous
A lightweight AI agent framework for TypeScript.
ishaand0314
Analyzes an AI agent session transcript and reports how much of the context window is live signal versus rot, plus a projected turns-until-compaction estimate.
...morepaulrichez
Run LLMs 100% in the browser via Transformers.js (WebGPU/WASM) — a local, keyless AI provider for aparté. Streams tokens off the main thread in a Web Worker.
...morepugstro
Spectrum-based fault localization for Vitest and Jest — ranks the lines most likely to be your bug.
Kadropic Labs
Official Python client for the LEO Soul hosted API (metacognitive layer for LLM agents).
Mistlight
An autonomous coding-agent orchestrator: hand off a well-specified task and return to reviewable, tested work.
Vinay karode
A workflow engine for AI agents
El-Qajjam Mohammed <[email protected]>
Enterprise-Grade Workflow Orchestration for Python
Rawson Consulting B.V.
Run a prompt through a LangChain (system + human) chain over Gemini on Vertex AI; optional LangSmith tracing.
AI-driven UI/UX automation & testing. Drives any software through its real UI (web, desktop, or pixels) — no target-app API required.
...moreml-agent-orchestrator
Closed-loop automated ML experiment engine driven by Claude Code (editor) and Google Antigravity CLI (evaluator), with git-based state decisions, persistent agent sessions, context-rotation memory, an AST code graph and a temporal experiment knowledge graph.
...morepyds-ai contributors
Data science and LLM work from a notebook, without writing much code. The LLM writes the query and the words; a deterministic engine computes the answer.
...moreGitHub Actions
AI-driven security audits — full-repo or diff/PR-scoped — for Claude Code, Gemini CLI, Cursor, and GitHub Copilot. Profiles the repo, designs tailored investigation lenses, runs them, verifies every finding, adversarially reviews high-impact ones. Install
...moreyseiren87
Scaffold platforms, services, and AI agent wiring (Cursor/Claude) for YJ architecture repos.
Haoming Luo
Agent-oriented finite-element workflow tools built on DOLFINx/PETSc.
git time-travel for any AI coding agent — undo a bad Codex/Claude/aider session in one command.
Jose A.
The dotagents CLI: install and manage a portable ~/.agents config for AI coding agents
Maarten Grootendorst, Jay Alammar
The code for the book 'An Illustrated Guide to AI Agents'
CodeNexus Contributors <[email protected]>
The context engine for AI coding agents - reduce tokens by 50-70%
Local-first multi-agent coding session archive tooling — discover, export, and baseline your AI coding sessions