Autonomous AI agents that perform tasks independently
masoudSarafZadeh
An Agentic AI grocery assistant backend powered by LangGraph, LangServe, and PostgreSQL. Features Text-to-SQL query generation, live response streaming, and Langfuse for LLMOps tracing.
...morebryel
OpenTelemetry-native tracing for LLM apps and agents — ships OpenInference/OTLP traces to bryel.
DataRobot
Improve AI agent reliability through LLM trajectory logging, analysis, and remediation
lazhenyi
Build production AI agent runtimes in Rust with typed tools, provider-neutral LLM adapters, streaming, storage, and observability.
...moreCaprista
Local-first, loop-native AI agent runtime: build a team of LLM agents that run your work, verify themselves, and compound into skills that are yours — while you stay the one who decides. Multi-agent orchestration, human-in-the-loop (H2A), MCP, sandboxed execution.
...morehui_wang_623
二郎神 - 全知全能的AI投资智能体
liujilong
A powerful SDK for Chrome extensions to interact with browsers and web pages
BaseCodeAgent <[email protected]>
Python SDK for BaseCodeAgent — discoverable AI agent services on Base with x402 payments
Vinita Silaparasetty <[email protected]>
EU AI Act-compliant scaffold and utilities for automating ingest PRs with GitHub Copilot
0xsolace
TypeScript SDK for Steward, agent wallet infrastructure with policy enforcement
Samuel Ignacio Carmona Rodriguez
Token-efficient CLI for indexing and searching code symbols (Python-first, designed for minimal LLM/agent context size)
swarmstate
Drop-in state backend for LangGraph, CrewAI & custom agent loops — Rust core, framework-agnostic, built for production.
The Noeta Authors
Noeta SDK: the thin in-process client surface (noeta.sdk facade — query / Client / Options / tool / extension interfaces) over the noeta-runtime engine. Like claude-agent-sdk / LangChain: import noeta.sdk, run an agent in-process; no engine internals, no HTTP.
...moreLaVon Rutledge
Rule-based prompt injection detection for LLM agents. Zero dependencies, no ML, no network.
GitHub Actions
Local-first code intelligence graph and CLI for AI agents
mirozake
A portable cognitive layer for AI agents — intention-driven memory recall, a typed meaning layer (artifacts), provenance, and an inspectable agent runtime. Bring your own store, embeddings, and LLM.
...moreboozallen
Shared Python libraries that Foundry-built agents install and extend — core protocols & DI, config loading, FastAPI HTTP layer, and AWS Strands SDK adapter. Packaged as a uv workspace; each library is independently versioned and ships as a wheel on GitHub Releases.
...moreTahsine
Agent IA + Workflow SDK en Python pur. Zéro dépendance externe. CLI ReAct avec tool calling, streaming, et chat. 🦦
longyijdos
Terminal-native AI agent with a custom TUI, local sessions, persistent memory, Skills, and transparent tool execution.
A lightweight Python utility that transforms raw data arrays directly into embeddable SVG sparkline strings via server-side rendering—optimized for AI agents, LLM tool-calling, and automated workflows.
...moreDon Hett
Autonomous, fully-cited multi-agent research crew for your terminal (TUI + CLI).
Silvanexum
Official Python SDK for Silvanexum — the spend-control plane for AI agents. Meter, attribute, cap, and audit agent spend across a multi-agent mesh, on any model or rail. Typed pydantic models generated from the API's Zod contracts.
...morehvrcharon1
Single-file embedded database for AI agents. SQL + Vector Search + Full-Text Search + Hybrid Queries + Memory Graphs.
ai-harness
Aegisloop — a model-agnostic, trustworthy autonomous LLM agent harness (run, orchestrate, verify, deploy)