cd /news/ai-safety/kitforge-generate-an-ai-agent-manife… · home topics ai-safety article
[ARTICLE · art-43874] src=agent-kits.com ↗ pub= topic=ai-safety verified=true sentiment=↑ positive

KitForge–generate an AI agent manifest; scaffold with enforced approval gates

AgentKits released KitForge, an open-source Python tool that generates LangGraph-style AI agents with enforced safety guardrails, including authority budgets, HMAC-chained audit trails, human-in-the-loop gates, and circuit breakers. The tool aims to address the gap in agent safety frameworks where controls are often not enforced, providing deterministic enforcement and tests to prove violations are stopped. KitForge is available under MIT license and generates agents with an attribution requirement.

read2 min views1 publishedJun 29, 2026

Tools · open source

A deterministic scaffold that turns a validated blueprint into a LangGraph-style agent — with a safety layer whose guardrails actually enforce. Python, MIT, no account. Everything it generates carries a “Generated by www.agent-kits.com” attribution.

Why this exists. Most “agent safety” frameworks describe guardrails the code never enforces — an audit verify that returns true, budget counters that never block. KitForge is built the opposite way: the controls are deterministic gates around the model, and the repo ships the tests that prove they stop a real violation. Run python -m pytest tests/

and watch a tampered audit log fail verification and a rejected approval halt the action.

What enforces #

Authority budgets that block

Tool-call, token, and wall-clock counters decrement and raise when exhausted. The agent loop stops — it does not log a warning and continue.

Audit trail that fails on tamper

An append-only, HMAC-chained log. verify() recomputes the chain and returns false if any entry was altered, reordered, or deleted. Not a no-op.

Human-in-the-loop that halts

A rejected or timed-out approval raises and the guarded action never runs. Approval is required structurally, not requested politely.

Circuit breaker + output validation

A breaker opens after repeated tool failures and refuses further calls; tool output is validated against its declared schema before it touches agent state.

Design one in your browser #

Sketch an agent here. You get a valid blueprint.json

to save and feed to KitForge locally — and a one-click check of the design in the Compliance Scanner. The code itself is generated on your machine by the Python CLI; this builds the blueprint it runs on.

Add a name and at least one tool to build.

Quick start #

unzip kitforge.zip && cd kitforge
pip install pydantic           # the only runtime dep
python -m pytest tests/ -q     # 13 enforcement tests pass

python -m kitforge demo -o ./my-agent
cd my-agent && export KITFORGE_AUDIT_KEY=$(openssl rand -hex 32)
python main.py                 # runs the loop; HITL gate stops 'publish' until you approve

Honest scope #

  • Python + LangGraph patterns only. The generated graph runner is intentionally minimal; swap in langgraph.StateGraph

for production — the safety wiring is identical. - Generated tools are [MOCK]

stubs. Wiring them to your real systems (and your real approver — Slack, email, web) is the last mile, and it's yours. - The framework enforces the controls it ships; it is not a substitute for a security review of your specific deployment.

Part of the AgentKits governance tools. See also the Compliance Scanner and Risk Assessment.

── more in #ai-safety 4 stories · sorted by recency
── more on @agentkits 3 stories trending now
sponsored brought to you by zahid.host 4,200+ EU-deployed projects
reading about agents? ship yours in a single git push.

Run your AI side-project on zahid.host

EU-based hosting, git-push deploys, automatic HTTPS, no cold starts. Free tier with a custom domain — perfect for shipping the agent you just read about.

$git push zahid main
Live at https://your-agent.zahid.host
Get free account → Pricing
from €0/mo · no card required
LIVE [news/kitforge-generate-an…] indexed:0 read:2min 2026-06-29 ·