Klent

7 posts

Klent banner
Klent

Klent

@klentdev_

Stop your AI agents from shipping bad actions to prod. Millisecond policies, human‑in‑the‑loop approvals, replayable audit log. Works with any framework.

Global Katılım Mayıs 2026
6 Takip Edilen2 Takipçiler
Sabitlenmiş Tweet
Klent
Klent@klentdev_·
Introducing Klent — the control plane for AI agents. Runtime policies. Human-in-the-loop approvals. Replayable audit trail of every action your agent takes. Works with Anthropic, OpenAI, or your own orchestrator. TS + Python. → klent.dev
Klent tweet media
English
0
0
2
22
Klent
Klent@klentdev_·
And — live on HN now: news.ycombinator.com/item?id=481363… Happy to answer questions in the thread, especially the obvious "couldn't I write this myself?" (yes, and Stripe / WorkOS / LaunchDarkly exist anyway).
English
0
0
0
9
Klent
Klent@klentdev_·
Built a sync policy engine that sits in front of every tool call your AI agent makes. 5 effects: allow / deny / modify / steer / approve. Sub-50ms. TS + Python SDKs. MCP server too. Demo ↓ — klent.dev
English
4
1
2
53
Klent
Klent@klentdev_·
@aistartuplabs That's the design split vs `deny`: `deny` returns a structured "blocked, here's why" so the agent retries with new params. `modify` rewrites silently but the result wraps a note (which policy fired, what changed) — agent can react or ignore, up to the loop.
English
0
0
1
13
Nick Stebbings | AI Startup Labs
Nick Stebbings | AI Startup Labs@aistartuplabs·
@klentdev_ The sub-50ms thing is what makes this actually usable. We hit the same wall building approval gates for AI execution, anything over a few hundred ms and the agent flow just falls apart. Early versions were painful. One thing I keep running into though, when you modify a call and the agent already has a tool schema locked in, does the engine rewrite the params before they hit the tool or does the agent itself need to know the schema might change underneath it?
English
2
0
0
32
Klent
Klent@klentdev_·
@aistartuplabs Engine rewrites the params before they hit the tool — schema stays locked, only the values change. Tool always sees valid input matching its declared signature, so agent code doesn't need to know anything was touched.
English
0
0
0
7
Klent
Klent@klentdev_·
The MCP angle is what makes it click — @klent/mcp-server is stdio, drop it into Claude Desktop / Cursor / any MCP client, every tool call goes through the policy engine. Zero SDK code on the agent side.
Klent tweet media
English
0
0
1
25
Klent
Klent@klentdev_·
Every decision lands in the audit timeline — which policy fired, what got rewritten, who approved, and how long it took. Built for the times your agent does something weird and you need to know exactly what happened.
Klent tweet media
English
0
0
0
15