Prismor helps enterprises control their agents' identity, access, and runtime actions
$ curl -sSL https://prismor.dev/install | shThen run prismor setup · Setup guide · View script
USE_CASES says agents without inline approval get DENY plus a queued review. After an admin approves, should the client retry that call, or does Prismor resume it? A short client-side example would help
Being able to individually disable MCP and plugins per agent offers a really practical level of control granularity
using it for a month now and it's been solid, genuinely happy to see this
AI agents can run commands before you get a chance to review them. This repo adds a checkpoint
Your agent is about to call a tool and you have no pause button in the session
Your guardrail can warn you and still wave the command through. Prismor's docs make the distinction explicit: observe only logs; enforce can block, but warn/log actions still allow the call
a seatbelt for claude code
open-source tooling that answers a real bill question always finds users
Love the MCP gateway angle. One policy layer across everything is the right abstraction
This is a real gap. The agent part gets all the attention, but visibility and control are what make it usable in production
nice take on agent iam, the guardrail scoping feels solid. how do you handle secret rotation across delegated sub agents?
this is genuinely needed. most agent stacks rn are a black box once you deploy them, and the "we'll add observability later" crowd finds out the hard way when something exfiltrates a token
super cool product!
Tried it for 3 of my repositories. Super awesome man!
I think this is a very solid approach
too good
security is key especially as models become increasingly capable!
so cool!
Love seeing tools that keep agents safe
Coding agents can run shell commands, install packages, call MCP tools and touch your secrets. Maybe we should watch them
Auditors will ask about the policy itself next: who wrote that rule, who approved it, and which version was live when the call was allowed. Do you version and sign policies alongside the decisions?
Looking for a promising tool: Prismor. Tell me something is wrong in the agentic coding landscape without telling me something's wrong
if you use Codex or Claude Code, you probably need this
bookmarked, thanks for sharing
bro this is actually clean, i've had claude code almost run rm -rf on my server once. policy checks would've saved me
the observe mode is the part i'd want tested: how often does it flag legitimate shell commands, and who maintains those policies when the repo changes?
Honestly, AI trading bots need this more than humans
gm, open source control plane that gates every tool call sounds like the missing guardrail. how heavy is the latency?
enforce mode saves wallets tbh
the enforce vs observe switch is smart! teams can see the blast radius before
Local first security for agents is a strong direction. Secret redaction is table stakes, but policy enforcement around tool calls and package installs is where this gets really interesting
This is awesomeee
Hats off for providing us with this!!
As enterprises are adapting agents into their workforce, security becomes very crucial part of the workflow. Looking forward for great work
Wrap your agent framework with Prismor in one step. MCP, the OpenAI Agents SDK, LangChain, CrewAI. Your existing agents keep working.
Every tool call routes through Prismor before it executes. The agent has no path around it.
Your active policy decides each call: allow, block, or mask. Secrets never reach the model. Destructive commands never run.
Read the full timeline of every agent action in the dashboard: arguments, outcome, user, session. Export it when compliance asks.
Update policies from the CLI as your conventions change. Every rule is versioned and reviewed by a teammate, same as infra config.