#agents

Gradient descent, but the parameters are agents — a parallel, asynchronous framework for self-evolving agents (skills, prompts, harnesses). Diffs are the gradients; the aggregator is the optimizer.

Local-first, inspectable memory for coding agents: durable context across sessions and repositories, code-aware recall, bi-temporal history, MCP, and a self-hosted WebUI.

Streamline your workflow with Lynkr, a CLI tool that acts as an HTTP proxy for efficient code interactions using Claude Code CLI.

No repository description published.

Outlit SDK

Verification guards for OpenAI Responses API - Verify AI agent outputs before execution

Local agent infrastructure in one stdlib-only Go binary

Help your agent remember what matters. Keep preferences, carry context across sessions, and bring your memory to the next agent.

A runtime for reliable multi-agent systems with durable workflows, resumable execution, and human-in-the-loop control

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

The TinyCloud Javascript SDK includes client libraries for node, browser, and CLI. These clients have built in tools for authentication, authorization, and capability delegation with TinyCloud

No repository description published.

Multi-agent swarm orchestration for Laravel, built on Laravel AI.

Durable sandbox lifecycle orchestration for AI agents built on Durable Workflow.

Modular framework for building LLM workflows and multi-agent systems

Ship fast. Ship right. Ship everything. Ship accountably. AI-powered dev system: slash commands orchestrate specialist agents from idea to hardened production. Imports godplans plans and godaudits reports; artifacts as .mdx.

No repository description published.

Toolkit for testing and packaging portable AI agents across various LLMs, frameworks, and deployment targets

Drive local coding-agent CLIs (Claude Code, Codex, any ACP agent) from Rust behind one abstraction: transport kind x harness kind

Portable workflow engine, runtime adapters, hooks, and kits that bring evidence-gated process discipline to agent tools.

Change Risk Anti-Patterns (CRAP) metric for Rust projects

A cognition aware database engine for AI agent memory. Purpose built in Rust with WAL, HNSW, knowledge graphs, and speculative context pre assembly. Not a wrapper, a ground up storage engine that thinks.

Options for creating a Microsoft Agent Framework Agent instance.

Provides Anthropic-specific registration extensions for MafPoolManager, enabling integration via Microsoft Agent Framework.

Provides Gemini-specific registration extensions for MafPoolManager, enabling integration via Microsoft Agent Framework.

Provides Mistral-specific registration extensions for MafPoolManager, enabling integration with local LLMs via Microsoft Agent Framework.

Agent-friendly CLI for Palo Alto Panorama object management: find IPs, dedup & safely merge objects, audit references, and enforce naming — dry-run by default, JSON & set-command output.

Fast hybrid code search for agents. Pure Go, drop-in MCP-compatible with semble.

The agent framework where the model never holds the trigger — every consequential action clears your policy first, waits for a human when it matters, and lands on a record you can verify. Build on it, or put it around the agent you already have.

Built from the ground-up for agents, Vessel Browser is an open source AI browser for Linux/Mac/Windows that provides a durable state, MCP control, and BYOK with full autonomous browsing. Use with Hermes Agent, OpenClaw, or connect to your favorite API provider.