#agent-framework

The GEP-powered self-evolving engine for AI agents. Auditable evolution with Genes, Capsules, and Events. | evomap.ai

Autopus-ADK is of the agents, by the agents. for the agents. Multi-model orchestration (consensus/pipeline/debate/fastest). Architecture-as-Code, Lore decision tracking, SPEC/EARS engine.

Give your agent a proper IDE and OS. The sensorimotor cortex for coding agents (OpenCode + Pi), part of CortexKit: symbol-aware edits, semantic search, code health, fast grep/glob, bash compression, background tasks, PTY.

Extensions for Microsoft Agent Framework

A composable framework for building reliable LLM agents on a harness you fully control. The same code runs the agentic loop on every model tier, local 4B to frontier with tool-call healing, verification, and durable crash-resume, on a typed 12-phase engine where every step emits an event you can hook into. Effect-TS, MCP-native, MIT

Define AI agent roles in YAML and run them anywhere: CLI, API server, or autonomous daemon

The agent loop for Rust — stream from 7 LLM protocols, run tools, loop until done.

A Go framework for the microagents architecture with dynamic discovery — specialized agents and tools that register their capabilities with a shared registry, find each other by logical name at runtime, and coordinate without a central conductor.

A Go toolkit for building AI agents and applications across multiple providers. Unified LLM client, agent framework with handoffs, tool calling, streaming, structured output, MCP integration, and cost tracking.

Polyglot AI agent service — knowledge chat, tools, durable checkpoints, human-in-the-loop, and multi-participant conversations over one schema-driven WebSocket protocol. Built on the smooth-operator-core engine (5-language parity). Deploy to Kubernetes, AWS serverless, or run locally. Hosted at lom.smoo.ai.

El repositorio no publica descripción.

The agent framework where every run is durable, replayable, and resumable by default.

Unbounded context. Memory that manages itself. One session, for life. The hippocampus for coding agents, part of CortexKit.

Self-hostable AI agents you can actually leave running — durable crash-resume, governed autonomy, seccomp sandbox, offline-replayable workflows, CI-native eval. Async-Python, YAML-config, multi-provider (OpenAI/Anthropic/Cloudflare), MIT.

The .NET library to build AI agents with 30+ built-in connectors.

Manifest-driven 21-stage agent pipeline for Python — 5 LLM backends (Anthropic / OpenAI / Google / vLLM / Claude Code CLI), tools, skills, memory, sandboxed CLI runs, MCP. The engine behind Geny. Apache-2.0.

Start a run in your terminal and walk away. Get pinged when it finishes, or needs you. Every step is a readable trace you check before anything ships.

An open-source terminal coding agent runtime and CLI for real project work.

Production-grade Go SDK for building AI agents with long-term memory, knowledge retrieval, and voice — runnable as a library, a daemon, or a real-time pipeline.

Open-source compiler for AI agents. Write one crewhaus.yaml; compile it to a CLI, a Slack bot, and an eval harness from the same spec. Apache-2.0.

Local-first, state-driven AI agent platform. Plan-review before execution, capability-gated tools, BYO LLM (Ollama / Anthropic / OpenAI). Tauri desktop + Go runtime.

A feature-full starting point for production agent applications on Tangle.

Per-project AI coding harness for Claude Code · Cursor · Codex. Profiler + 10-dim interview build a different harness for every project.

Model-agnostic agent harness for Elixir

Official extensions for gopact

TypeScript harness for building personal AI agents with durable memory — agents that live across your channels (CLI, Teams, iMessage, mail, voice), use real tools, and stay coherent across turns. The runtime behind @ouro.bot.

Self-hosted AI agent harness in a single Go binary — writes, sandbox-tests and repairs its own tools, and lets Claude Code, Codex and any MCP client build and share them.

Runnable examples for gopact

Embeddable agent kernel for durable, provider-neutral LLM agents with permissions, pluggable tools, observability, and subagents.