Autonomous AI agents that perform tasks independently
ai-agent-recovery
Context recovery for AI agents — analyze fatigue, compress context, improve token efficiency
Hrishikesh Thakre
A lightweight local CLI acceptance gate for AI-generated engineering work
xamong
AI agent workbench desktop for terminals, MCP tools, Capability Registry, and live UI rendering
forgewisp
Forgewisp — safe, function-calling AI agents for the browser. Register your own functions as validated tools, with risk-tier execution, OpenAI-compatible streaming, dual reasoning streams, and an audit log. Runs entirely client-side.
...moreSiliSocS: a configurable, extensible framework for multi-agent social simulation and experimentation, organized by the EASE decomposition (Environment, Agents, Simulation engine, Evaluation)
...moreTulip Labs
Drop Tulip's control runtime (admit() gate + tamper-evident audit) into the agent framework you already use — LangChain, LangGraph, CrewAI, the OpenAI Agents SDK, LlamaIndex.
...moreMubit
Minima CLI: cost-aware LLM model routing — recommend cheaper models, backed by Mubit memory.
Tilth — minimal long-running agent harness against any OpenAI-compatible endpoint. Brain/Hands/Session split, Ralph loop, four memory channels.
...moreAbhinav
A deterministic supervisor that runs Claude Code and Codex CLI through a Plan -> Implement -> Review -> Test workflow
RapidAgent <[email protected]>
Plug-and-play agentic framework with multi-backend, guardrails, and Azure AD support
AgentPal
An open Pal Pack standard for building lightweight Pal teams — portable companions that package persona, knowledge, skills, memory, workflows, and verification for agent runtimes like Codex and Claude Code.
...moreTiao553
AI-powered assistant for Harness-based software delivery, helping automate CI/CD, testing, deployments, and pipeline optimization with faster, safer, and more reliable workflows.
...moreA two-LLM, refute-first agentic source-code vulnerability scanner — wide-net navigate, skeptical refute, jailed in docker. Bring your own LLM.
...morevystartasv
CLI to make your agent framework WWA-compatible — one command
Xiaoguai contributors
Python convenience wrapper around the Rust xiaoguai CLI.
"Ockham.sh" <[email protected]>
AI agent framework for data analysis — write and execute Python code to answer questions about data
rajudandigam
Optional OpenAI Agents JS tracing processor integration for AgentInspect local traces
Mark Nottingham <[email protected]>
Characterize the clients hitting a web site by analyzing its access logs.
Catch zombie prompts — retracted AI rules that crept back into your .cursorrules / CLAUDE.md / AGENTS.md — with a verifiable receipt.
...moreCouplet Contributors
Couplet agent engine — ACS v1, harness, LLM client, tools, and skills
martinoyovo
Local-first, fully offline AI assistant for an NGO's case data. A local Ollama model answers only through MCP tools, with full provenance in the UI. Nothing leaves the machine.
...moreigdigitallab
An IDE for managing software projects with the Claude Agent SDK — a web cockpit + a kanban board that auto-runs cards as full-auto agent sessions.
...moreTerminal-native AI Coding Agent — SOP-driven, multi-provider LLM, autonomous self-healing
Archit Dwivedi
Streaming, declarative multi-agent workflows for Deep Agents.