Agent Harness Python Packages

trustgraph-embeddings-hf

Write context once. Run agents anywhere. Own your data and the models.

desloppify

Agent harness to make your slop code well-engineered and beautiful.

soothe-sdk

🛀 Soothe - An autonomous expert system engineered to orchestrate complex workflows and execute long-duration tasks with precision and persistence.

soothe

🛀 Soothe - An autonomous expert system engineered to orchestrate complex workflows and execute long-duration tasks with precision and persistence.

trustgraph-base

Write context once. Run agents anywhere. Own your data and the models.

trustgraph-cli

Write context once. Run agents anywhere. Own your data and the models.

soothe-cli

🛀 Soothe - An autonomous expert system engineered to orchestrate complex workflows and execute long-duration tasks with precision and persistence.

trustgraph-vertexai

Write context once. Run agents anywhere. Own your data and the models.

trustgraph-flow

Write context once. Run agents anywhere. Own your data and the models.

trustgraph-ocr

Write context once. Run agents anywhere. Own your data and the models.

ait-vcs

AI coding agents should work in attempts, not your working tree

trustgraph

Write context once. Run agents anywhere. Own your data and the models.

trustgraph-bedrock

Write context once. Run agents anywhere. Own your data and the models.

soothe-daemon

🛀 Soothe - An autonomous expert system engineered to orchestrate complex workflows and execute long-duration tasks with precision and persistence.

trustgraph-mcp

Write context once. Run agents anywhere. Own your data and the models.

trustgraph-unstructured

Write context once. Run agents anywhere. Own your data and the models.

vaultspec-core

A full-featured spec-driven harness for coding agents (and us, humans)

memtomem

Markdown-first, long-term memory infrastructure for AI agents. Hybrid BM25 + semantic search across markdown/code files via MCP.

memtomem-stm

Short-term memory proxy gateway with proactive memory surfacing for AI agents

researchharness

A lightweight, general-purpose harness for tool-using LLM agents, fair benchmark evaluation, harness baselines, and personal assistant workflows.

graphrefly

Reactive harness layer for agent workflows. Describe automations in plain language, trace every decision, enforce policies, persist checkpoints. Python. Zero dependencies.

agent-harnesses-mcp

🏆 Curated, ranked list of AI agent harnesses (100+) — plus an MCP server, llms.txt & JSON so agents can recommend them too. Rescored weekly.

sponsio

Deterministic safety solutions for probabilistic AI agents

langchain-task-steering

Task-steering — Implicit state-machine middleware for LangChain v1 agents. Ordered task pipelines with per-task tool scoping, dynamic prompt injection, and composable completion validation.