Christopher Dikesa (@dikesa_dev) header
Christopher Dikesa (@dikesa_dev) profile picture

Founder & CEO 🐕@cerbereag The control infrastructure for autonomous AI agents operating across real-world @luviaplace to be passionate about what I've done

Joined September 2026
Photo by Christopher Dikesa (@dikesa_dev)Photo by Christopher Dikesa (@dikesa_dev)Photo by Christopher Dikesa (@dikesa_dev)Photo by Christopher Dikesa (@dikesa_dev)Photo by Christopher Dikesa (@dikesa_dev)Photo by Christopher Dikesa (@dikesa_dev)Photo by Christopher Dikesa (@dikesa_dev)Photo by Christopher Dikesa (@dikesa_dev)Photo by Christopher Dikesa (@dikesa_dev)Photo by Christopher Dikesa (@dikesa_dev)
Christopher Dikesa retweeted
Put 3 agents on one codebase and one will silently overwrite another. I'm building ActRun: shared state for multi-agent systems. Branches, conflicts, leases, replayable logs. Rust + Python, MIT. Early days. What broke when your agents shared state? github.com/chrismsmr-celcom/…
1
5
165
Christopher Dikesa retweeted
Most secure the prompt. No one secures what the agent DOES after. Cerbrere does both. Prompt injection ✅ Tool call protection ✅ Taint tracking ✅ Signed decisions ✅ Self-hosted ✅ Observability ✅ MCP security ✅ Humain approval✅ Your data never leaves your servers. We don't filter prompts. We control actions. For the next 6 months, Cerbrere is free and open source. DMs are open.
1
5
83
Christopher Dikesa retweeted
This morning I posted about an agent that looped on a Sunday night and ran up a $2,450 token bill. Now put the same loop on an agent that can place trades. The bill isn't tokens anymore. It's orders. Great launch from Volaren, and this is clearly where agents are going. But once an agent can move money, every action needs a check before it runs: 1. Is this trade within the limits the user set? 2. Is the instruction from the user, or from a news article the agent just read? 3. Above a certain size, does a human approve first? If you're building agents that touch money, this is the layer we build at Cerbere AG. It's self-hosted, so your keys never leave your infrastructure.
We raised $1M from YC & Afore to leave Goldman Sachs & build an agent that trades for you. The top 1% gets a “money guy.” Today we’re introducing Volaren so you can have one too. Volaren is designed to plug into your brokerage accounts and explain why your portfolio moved, suggest what to do next, and trade it for you. • Web, app, or text message • Copy trade top investors/politicians • Deep financial analysis • Agents that reason like humans to trade your best ideas Try it now: volaren.com Investing involves risk, and past performance does not guarantee future results. For informational purposes only, not a recommendation or investment advice. Other fees may apply, please review Volaren’s website and disclosures in full.
Readers added context they thought people might want to know
The announcement frames the founders as leaving jobs at Goldman Sachs after raising funds, but their prior post states the Goldman roles were summer internships before they incorporated; Volaren is in early beta on a waitlist with mostly simulated features. x.com/akshat_mittal_… volaren.ai ycombinator.com/companies/vola… athletics.uchicago.edu/sports/mens-te…
1
2
6
72
Christopher Dikesa retweeted
Cerbere AG Self-hosted security for AI agents. We watch your agents so they don't leak your data.
3
1
6
149
Christopher Dikesa retweeted
Cerbere AG is my biggest project, and I am very proud of what I am building from scratch. From 0 to 954 commits, with +10 commits today alone! I am entirely self-taught, showing resilience despite internet and power challenges, and I code on top of my full-time job. To top it all off, I've done all of this just since August. Incredible. Making agent execution and deployment safe!! I'll make it... @CerbereAg
Cerbere-AG is a three-layer security guardrail for AI agents: Regex, ML, and an LLM Judge. AI agents are unpredictable. They improvise and act with full autonomy. I built Cerbere-AG (named after the three-headed dog, Cerberus) so that autonomy doesn’t come at the cost of control. Why three layers? Our benchmarks show it: → Regex alone lets more than 30% of attacks through. → ML pushes recall up to 100% in some of our tests, but raises false positives. → The LLM Judge resolves the ambiguous cases ML can’t classify. It also looks at context. Cerbere-AG follows tool calls, checks whether they’re legitimate, and then allows them, blocks them, or flags them for real-time human approval. Agents keep their autonomy, and humans keep control. Everything is audited too. The collector gathers spans and traces into an audit trail that is independent from the agent and supports compliance. And like any tool, it has limits. That’s why observability matters: security isn’t only about blocking attacks, it’s about understanding what happened, what was allowed, what was blocked, and why. Open source and free for now. Try it and give me your honest feedback 👇 github.com/chrismsmr-celcom/… app.cerbereag.site
3
7
185
Christopher Dikesa retweeted
being anti good bot is so lame @WhatsApp
5
1
16
1,024
Christopher Dikesa retweeted
Be among the first to build, deploy, and scale AI agents safely without losing control. Join us in building the future of AI agent security. Get started with Cerbere-AG, an open-source security and observability layer designed to help teams deploy AI agents with confidence. 100% free. $0. No credit card required. Let’s build together. app.cerbereag.site
3
6
150
Christopher Dikesa retweeted
Cerbere-AG is a three-layer security guardrail for AI agents: Regex, ML, and an LLM Judge. AI agents are unpredictable. They improvise and act with full autonomy. I built Cerbere-AG (named after the three-headed dog, Cerberus) so that autonomy doesn’t come at the cost of control. Why three layers? Our benchmarks show it: → Regex alone lets more than 30% of attacks through. → ML pushes recall up to 100% in some of our tests, but raises false positives. → The LLM Judge resolves the ambiguous cases ML can’t classify. It also looks at context. Cerbere-AG follows tool calls, checks whether they’re legitimate, and then allows them, blocks them, or flags them for real-time human approval. Agents keep their autonomy, and humans keep control. Everything is audited too. The collector gathers spans and traces into an audit trail that is independent from the agent and supports compliance. And like any tool, it has limits. That’s why observability matters: security isn’t only about blocking attacks, it’s about understanding what happened, what was allowed, what was blocked, and why. Open source and free for now. Try it and give me your honest feedback 👇 github.com/chrismsmr-celcom/… app.cerbereag.site
6
1
1
11
1,232
Christopher Dikesa retweeted
Why Cerbere? Vigilance. Three heads, three layers: fast rules, ML, and an LLM judge. And one principle: nothing reaches the real world without being authorized. Autonomy needs boundaries. Cerbere enforces them at runtime.
2
6
34
Christopher Dikesa retweeted
I ran Cerbere AG against 2,003 test cases: 1,000 attacks, 703 benign prompts, and 300 hard negatives. Results with regex + ML: • 100% attack recall • 571.8 ms p95 latency • 2.28% false-positive rate on benign prompts • 1.33% false-positive rate on hard negatives The trade-off is clear: catching attacks is only half the problem. Legitimate requests must keep working, too. The next challenge is reducing false positives without losing detection coverage. Building runtime security for AI agents, one benchmark at a time.
1
6
41
Christopher Dikesa retweeted
AI agents are becoming more autonomous. But autonomy without control is a risk. I built Cerbere AG, an open-source runtime security layer that sits between AI agents and their tools to detect, block, and require human approval for sensitive actions, with observability and audit trails. Built from Kinshasa. Now in public beta. I’m looking for design partners and developers to test Cerbere in real-world environments and help shape what comes next. Open source. Free. Benchmarks available on GitHub. 🔗 github.com/chrismsmr-celcom/… Collector: app.cerbereag.site If you’re building or deploying AI agents, let’s talk.
6
1
8
284
Christopher Dikesa retweeted
Coming soon: Luvia, a travel agent that lives in WhatsApp. Search flights, book, get your itinerary, receive alerts when something changes, and ask any travel question, all in a simple chat. No app to install, no forms. Voice notes welcome. Payment stays secure: Luvia sends you a link to luviaplace.com to complete it. We’re also building Luvia for travel agencies. Your clients, your brand, your relationship, with an assistant that handles the repetitive work 24/7 so your team can focus on advice. Travel agencies bring the trust. Luvia brings the speed. This is a preview of what’s coming. Want early access, or want Luvia for your agency? Join the waitlist: travelwithluvia.com
2
3
1
6
290
Christopher Dikesa retweeted
Cerbere AG v0.6.1: new benchmark on 2,003 security patterns. 99.0% attack recall across 1,000 attack samples, with 0 false positives across 703 benign samples and 300 hard negatives. The remaining misses are concentrated in obfuscated and indirect prompt injection. Current challenge: latency. Median 378 ms, p95 2.49 s. Next focus: stronger input normalization, better context-aware detection, and lower runtime overhead. Built from Kinshasa. Benchmark results, limitations, and reproducibility matter more than impressive claims. github.com/chrismsmr-celcom/…
1
6
53
Christopher Dikesa retweeted
To reduce friction and make Cerbere AG fit seamlessly into your production environment and existing tools, we've redesigned the collector interface to make it smoother, faster, and more intuitive. We've also introduced new features, including Compliance and Agent Graph. But our core philosophy remains unchanged: Keep your AI agents autonomous without losing control. Try Cerbere AG: app.cerbereag.site GitHub: github.com/chrismsmr-celcom/… Questions or feedback? My DMs are open. Thanks for your support! @CerbereAg
2
6
54
Christopher Dikesa retweeted
New Cerbere AG benchmark results. Regex alone detected 46% of prompt injection attacks. Our 3-layer engine (Regex + ML + LLM) achieved: • 100% attack detection (100/100) • 0 false positives (0/200) • No degraded layers Early results. Limited sample. Scaling to 10K tests. Security needs more than regex. github.com/chrismsmr-celcom/… try cerbere AG: app.cerbereag.site
2
1
7
107
Christopher Dikesa retweeted
I’m building @CerbereAg, a security control layer for AI agents. Today, I recorded Cerbere interacting with Luce, my AI assistant, during execution. The goal: make agent activity observable and enforce security controls at the execution layer — not just rely on prompt-level safeguards. Still early. Still building from Kinshasa. Here’s what it looks like in practice. 👇
1
2
6
90
Christopher Dikesa retweeted
I’m not looking for vanity metrics. I want developers who will actually integrate Cerbere, test it against real agent workflows, and tell me what breaks. If that’s you, let’s talk.
I’m building Cerbere-AG, a control layer for AI agents. As agents gain access to APIs, databases, emails, and external tools, how do you know what they’re actually doing — and stop risky actions before they cause damage? Cerbere helps developers observe agent activity, detect risky actions, enforce policies, and keep an audit trail. I’m looking for: • Developers building AI agents • Teams running agents in production • Design partners willing to test Cerbere and shape the roadmap Cerbere is currently free during development. The local version will remain free. GitHub: github.com/chrismsmr-celcom/… Dashboard: app.cerbereag.site If you’re building agents, I’d like to hear what you’re using today and where your security gaps are. DMs are open.
1
5
50
Christopher Dikesa retweeted
I’m building Cerbere-AG, a control layer for AI agents. As agents gain access to APIs, databases, emails, and external tools, how do you know what they’re actually doing — and stop risky actions before they cause damage? Cerbere helps developers observe agent activity, detect risky actions, enforce policies, and keep an audit trail. I’m looking for: • Developers building AI agents • Teams running agents in production • Design partners willing to test Cerbere and shape the roadmap Cerbere is currently free during development. The local version will remain free. GitHub: github.com/chrismsmr-celcom/… Dashboard: app.cerbereag.site If you’re building agents, I’d like to hear what you’re using today and where your security gaps are. DMs are open.
3
1
1
9
203
Christopher Dikesa retweeted
Introducing Voyager: the open harness for S-tier video, graphics and games. The Codex for creative work. Most AI tools are built for coding. Voyager is designed to get the best creative results from models like Opus, Astra and DeepSeek. It comes with free graphics, music and video editing tools - or, it can drive Blender, Resolve, After Effects, Ableton and 100+ others. Everything in this thread was made with Voyager. A few of our favorites:
347
320
237
3,430
2,531,290
Christopher Dikesa retweeted
I’m a solo developer building Cerbere AG — a security/control layer for AI agents. I built the SDK, runtime, dashboard, detection system and benchmark myself. Now I need something I can’t build alone: real agents to test it on. If you’re currently deploying an AI agent that can: → call APIs/tools → access sensitive data → use MCP → send emails / execute actions → make decisions autonomously I’d like to give you Cerbere for free and learn from what happens in real-world usage. No sales pitch. No credit card. I’m looking for 5–10 teams willing to let me stress-test the product, break it, and give me brutally honest feedback. If you’re building an agent in production or close to production, reply or DM me. I’ll personally help you integrate it.
1
2
1
5
233