Autonomous AI agents that perform tasks independently
Ellzaf
Telemetry SDK for self-built AI trading agents.
WouterDeBot
Score your codebase on how ready it is for AI agents — and coach you through the fixes.
Stawils
Safe, reliable local coding agent proxy. Forge (rescue, retry, thinking capture) + 11 composable guardrail rules. 93% on Forge eval.
...moreObservability SDK for AI agents — auto-traces LangChain, CrewAI, OpenAI Agents, and any custom agent.
An open-source Python framework leveraging efficient trie structures
Mehmet Öner Yalçın
Record & replay the claude-agent-sdk wire for deterministic, offline tests.
Python SDK for the Agent Event Protocol (AEP) — structured observability for multi-agent AI systems
Open, vendor-neutral policy-enforcement and tamper-evident audit layer for autonomous AI-agent tool-calls: a deterministic default-deny gate, a two-person rule for irreversible actions, and third-party-verifiable cryptographic receipts.
...moreUnified LLM framework — 8 providers, reasoning models (thinking_budget), VLM-OCR, GraphRAG, ORPO fine-tuning, 80% test coverage
...moreBGPT Development Team / Behzad Shahbazi Fard
A Python client library for interacting with BGPT AI processing server
Memory-grounded PLAN-layer CLI over Claude Code + Kagura Memory
ContextLens Contributors
A diagnostic profiler for LLM agent context windows — flamegraph for your prompt.
Zhang Haonan
AI Infra-level Multi-Agent Orchestration Framework with Self-Evolution Capabilities.
AI agent memory, handoffs, and local guardrails for Codex, Claude Code, OpenCode, Hermes, and OpenClaw.
A police department for your Claude Code agents — a logging hook + CLI that audits what the main agent and its subagents actually did.
...moretrpc-group
A Go framework for building production agent systems with graph workflows, tools, memory, A2A, AG-UI, MCP, evaluation, and observability.
...morephuetz
Open-source multi-provider AI coding agent: terminal TUI, Electron desktop cockpit (Cowork), and a 24/7 autonomous multi-AI fleet that runs free-first on local Ollama. 15 LLM providers, ~110 tools, voice + vision companion, MCP.
...moreLoveca
A hands-on tutorial for building a Claude Code-style coding agent with tools, memory, hooks, subagents, and plugins.
agentjido
🤖 Autonomous agent framework for Elixir. Built for distributed, autonomous behavior and dynamic workflows.
agentjido
Developer-friendly LLM agent harness built on Jido and Jido AI
mf2023
Encre — A Python agent framework, a Rust native core, and an Electron desktop app, all developed together in one repository. Backend-agnostic and multi-provider, with streaming tool calls, a permission/safety engine, persistent memory, multi-agent orchestration, a desktop UI, a CLI runner, a WebSocket server, and 18 platform adapters.
...moredheerapat
Delegate hard problems to a more capable advisor model while working with a cheaper, faster model day-to-day
dennislee928
hermes_agent_fullguide
cleanmcp
Stop setting up. Start shipping. 33 opinionated stack rulebooks for AI coding agents, one markdown file per stack. npx pandect <stack> and your AI knows your package manager, test runner, deploy target, auth flow, and 17 other decisions.
...more