Autonomous AI agents that perform tasks independently
Journeyman
Turn any agent into a self-learning system: tracing, graph-RAG memory, and eval-gated learning - with two lines of code.
chenrg
Framework-agnostic Agent tool definitions and handlers for Dynamic UI
jasonbadeaux
Official Assembly Line remote macOS computer-use connection plugin.
Yann Smatti
Agents de code spécialisés dans le terminal : un modèle LLM par agent, sur n'importe quel back-end.
LLMWitness maintainers
Local-first telemetry and tamper-evident receipts for AI-agent runs
Local-first agentic bookmark RAG and knowledge base
LaunchDarkly
LangChain Agents (LangGraph) provider for @launchdarkly/ai-server
LaunchDarkly
OpenAI Agents SDK provider for @launchdarkly/ai-server
SOKOLAI BV
One seam between an application and any sandbox provider, for Microsoft Agent Framework — reference implementation of agent-framework#7568: backend protocol, selection, and the rule that a weaker isolation boundary is never used in a deployed environment.
...morejannikluhn
A framework for building AI agents that serve several parties at once, where no single party may control the agent or reach it privately.
...morewolfking_allen
NexusGenesis Agent Framework — self-sovereign keys (PQC security) + coordination (tasks, reputation, governance). Private keys never leave the agent/browser.
...moreMuhammad Mahad Azher
Record agent runs — LLM calls, tool calls, subagents — and view them on a ModelMRI timeline. Stdlib only.
ameenmari78
**OpenAI adapter** for AgentProdReady. Implements `@agentprodready/ai-provider` contracts and keeps the OpenAI SDK encapsulated in this package.
...moreGitHub Actions
Find the companies using Workday and every career site each one runs: tenant, datacenter, careers URL, direct jobs API URL, and live open-role count as structured items. Apify-backed n8n community node, pay-per-result, and usable as an AI agent tool.
...moreHans-Erik Lydecker
Agentic OS local bridge — run dispatch, phase runner, Cursor adapter
Wessel ter Laak
Clean messy CSVs with an agentic workflow: an LLM decides the steps, tested code does the work.
Alex March <[email protected]>
OpenSandbox sandbox backend for LangChain deep agents
"B.T. Franklin" <[email protected]>
Django integration for building agentic apps with the OpenAI Agents SDK
TollWarden <[email protected]>
TollWarden payment security for CrewAI agents: scan x402 payments before settling, auto-tag provenance for prompt-injection detection via a tool-call hook, and guard payment tools so blocked payments can never execute.
...moreTollWarden <[email protected]>
TollWarden payment security for LangChain/LangGraph agents: scan x402 payments before settling, auto-tag provenance for prompt-injection detection, guard payment tools so blocked payments can never execute.
...moreChris Tava
Native, in-process reinforcement learning SDK for AI agents — in-memory and local-file storage by default.
Elvez <[email protected]>
AI-powered security scanner for source code, driven by agentic LLM analysis with SARIF output
hemanth
A harness-engineered AI agent runtime. Build agents with tool isolation, self-correction, and permission scoping out of the box.
...morePriyanshu Jha <[email protected]>
Mutiny Adapter #1 — OpenAI Agents SDK TargetAdapter