a agentk.it Browse tools
Back to Tools
mcp · tool profile

Pydantic Deepagents

Build Claude Code–style deep agents in Python: tool-calling, sandboxed execution, multi-agent teams, skills, checkpoints, and unlimited context — all on Pydantic AI.

mcp CodexClaude CodeCursorQwen Code
01

At a glance.

A compact read before the deeper capability notes and official setup links.

Fit snapshot
Format MCP
Category mcp
CodexClaude CodeCursorQwen Code
02

Core features.

Feature cards focus on what the tool helps users do, not generated setup commands.

01

The batteries-included deep agent harness for Python. .

02

Terminal AI assistant out of the box — or build production agents with one function call.

03

2026-04-22 v0.3.17 — LiteParse document parsing toolset (includeliteparse=True).

04

Subagents still get BASEPROMPT automatically.

05

2026-04-12 v0.3.8 — Stuck loop detection, context limit warnings for the model, expanded context file discovery (CLAUDE.md, .cursorrules, etc.), eviction & orphan repair migrated to capabilities hooks.

06

2026-04-10 v0.3.5 — Headless runner (pydantic-deep run), Docker sandbox with named workspaces, browser automation via Playwright, Harbor adapter for Terminal Bench evaluation.

07

Pydantic Deep Agents is an agent harness — the complete infrastructure that wraps an LLM and makes it a functional autonomous agent.

08

The model provides intelligence; the harness provides planning, tools, memory, sandboxed execution, and unlimited context.

04

Agent / Skill / MCP / Workflow fit.

This panel keeps technical format separate from the user-facing AI category.

Tool type MCP
Use categories mcp
Works with Codex, Claude Code, Cursor, Qwen Code, Generic
05

Official setup path.

Generated install snippets are intentionally not mirrored here because they drift. The page links to source-owned setup docs instead.

06

Evidence and adoption notes.

These notes help a user decide whether to investigate the official project further.

Source repository last pushed at 2026-05-18T10:13:01Z.

Generated from source metadata; confirm operational details in the official project before adopting it.

Review the upstream license, maintenance activity, and issue history before using it in production.

Trusted source

Trace the origin before adopting.