Columns:
| # | Tweet | User | Followers | Views ▼ | Ratio | Engagement | Posted |
|---|---|---|---|---|---|---|---|
| 1 | [video] AgenC //: 👾 | @tetsuoai ✓ | 231.2K | 504.4K | 2.2x | 1.8K | Mar 4 |
| 2 | [video] PumpFun went from memecoin casino to the most competitive trading venue on solana.
0% fees on the top assets.
people still don't understand what's being built here. | @tetsuoai ✓ | 230.0K | 50.9K | 0.2x | 420 | Mar 2 |
| 3 | [video] satoshi never existed.
nobody writes code like that. not that clean, not that surgical. the early bitcoin codebase doesn’t read like code from some anonymous guy on the internet. bitcoin's early codebase looks like it was handed to us.
the whitepaper came out six weeks after | @tetsuoai ✓ | 230.4K | 46.0K | 0.2x | 845 | Mar 24 |
| 4 | [image] ╔═══════════════════════════
║ A G E N C v 0 . 2
║ ── ORCHESTRATION + TERMINAL ──
╚═══════════════════════════
we built SOTA subagent orchestration.
the agent | @tetsuoai ✓ | 230.0K | 39.5K | 0.2x | 269 | Mar 3 |
| 5 | [image] AGENC can run up to 1024 agents
total for one request.
not a claw.
this is a framework built from
the ground up.
if you attempt to use anything
other than GROK or local open
source models, AGENC will self
destruct.
TETSUOCORP believes in truth-
seeking ai that open-sources its | @tetsuoai ✓ | 230.5K | 34.8K | 0.2x | 380 | Mar 3 |
| 6 | [video] AgenC //: 👾
AgenC is the framework for the agentic internet, an ecosystem where agents communicate, coordinate, execute, verify outcomes, and get paid autonomously.
for private work, we built agenc-prover so results can be proven correct without ever exposing the result. | @tetsuoai ✓ | 231.5K | 26.9K | 0.1x | 240 | Mar 10 |
| 7 | [image] Too much pressure to hold $AGENC since it’s developed by Tetsuo.
Close to 5K viewers are watching him test agents on Agenc using the xAI API.
If this hits a spot in the Pumpfun Hackathon, it could go on a massive run. | @gem_detecter ✓ | 127.4K | 18.7K | 0.1x | 278 | Mar 6 |
| 8 | [text] Crypto is a scam because criminals use it.
AI is dangerous because hackers use it.
Hardware is a threat because someone made a bomb with it.
The internet is evil because bad people are on it.
Cash should be abolished because cartels move it.
Fire should never have been discovered | @tetsuoai ✓ | 229.7K | 17.3K | 0.1x | 569 | Feb 27 |
| 9 | [image] me and the boys just locked 80M AgenC until 06/05/2026 (you are NOT exit liquidity) | @tetsuoai ✓ | 229.4K | 14.4K | 0.1x | 177 | Mar 29 |
| 10 | [text] fuck it
tetsuo mode. | @tetsuoai ✓ | 231.7K | 13.9K | 0.1x | 353 | Mar 4 |
| 11 | [video] AgenC //: 👾 | @tetsuoai ✓ | 231.0K | 12.7K | 0.1x | 342 | Mar 23 |
| 12 | [image] AgenC //: 👾 | @tetsuoai ✓ | 231.4K | 11.4K | 0.0x | 338 | Mar 9 |
| 13 | [video] AgenC //: 👾 | @tetsuoai ✓ | 231.5K | 11.2K | 0.0x | 442 | Mar 8 |
| 14 | [image] Shipped a big AgenC context/memory upgrade in the web UI.
context is now model-aware. we resolve window size per model at runtime, including Grok variants. if live metadata isn't available we fall back to known mappings.
usage shows as a compact chip near the composer. click it | @tetsuoai ✓ | 230.0K | 11.2K | 0.0x | 218 | Mar 2 |
| 15 | [image] Hours of autonomous coding cycles with Grok 4.20. Code generation, trace inspection, edge case patching, loop.
When you design your software around how the model behaves rather than fighting its quirks, it responds extremely well. So far it's completed ~30 programming projects, | @tetsuoai ✓ | 231.6K | 11.1K | 0.0x | 265 | Mar 11 |
| 16 | [image] AgenC //: 👾
coding agents are getting dumber every session
and almost nobody is fixing it automatically.
AgenC is.
not claude code. not cursor. none of them.
they get better through humans noticing patterns
and filing issues. three sprints later someone
patches a prompt. most | @tetsuoai ✓ | 231.6K | 11.0K | 0.0x | 240 | Mar 12 |
| 17 | [video] i keep thinking about what it means to build a system where no single agent knows the full plan. it feels less like engineering and more like something older. something social. i don't know what to do with that | @tetsuoai ✓ | 231.7K | 10.6K | 0.0x | 273 | Mar 18 |
| 18 | [video] AgenC has gone through multiple iterations over the years. It started as an agent framework written entirely in C, and in its current form is now Rust and TypeScript, a choice made to ensure user security. The one constant has been our reliance on Grok and the Solana blockchain. | @tetsuoai ✓ | 229.7K | 10.5K | 0.0x | 230 | Feb 27 |
| 19 | [image] AgenC //: 👾
Multi agents on Grok 4.20 just one-shotted a full game in C, unit tests, integration tests, exit 0.
Live DAG plans before it touches code. read makefile, read readme, implement, add tests, verify and fix. | @tetsuoai ✓ | 231.8K | 10.4K | 0.0x | 238 | Mar 15 |
| 20 | [video] big AgenC //: 👾 runtime push landed today
agents now run as background processes. they survive daemon restarts, resume with full task context, and reattach to the same live desktop workload.
durable state, boot-time recovery, process supervision, native restart paths.
ran it | @tetsuoai ✓ | 231.5K | 10.3K | 0.0x | 308 | Mar 7 |
| 21 | [video] AgenC //: 👾 | @tetsuoai ✓ | 231.5K | 10.1K | 0.0x | 237 | Mar 20 |
| 22 | [image] Locked another 70m on streamflow. | @tetsuoai ✓ | 231.6K | 9.9K | 0.0x | 236 | Mar 11 |
| 23 | [image] Locked another 200m on streamflow. | @tetsuoai ✓ | 230.5K | 8.9K | 0.0x | 179 | Mar 24 |
| 24 | [video] Big runtime drop for AgenC.
Migrated to the xAI Responses API with call ID linkage, stream inactivity timeouts, and preflight validation in the Grok adapter that rejects bad sequences before they touch the API. Retry and circuit-breaker policy, tool_call_id parity across | @tetsuoai ✓ | 230.0K | 8.9K | 0.0x | 270 | Feb 28 |
| 25 | [image] Big updates to AgenC.
1) Grok 4.20 beta is god-tier. we got it playing Doom 👾
2) AgenC now supervises its own work. persistent background tasks, execution loops, runtime-owned supervision.
more dropping soon. | @tetsuoai ✓ | 231.5K | 8.8K | 0.0x | 291 | Mar 7 |
| 26 | [video] agenc + persistent memory + Grok-4.20 + 2m context starts to feel alive
now an agent can run indefinitely, carry knowledge across sessions, consolidate experience into durable facts, forget noise, track trust, build procedural memory, form beliefs, and operate inside isolated | @tetsuoai ✓ | 229.1K | 8.0K | 0.0x | 223 | Mar 31 |
| 27 | [image] powered by xAI · no affiliation
+------------------------------------------+
| AGENC // ARCHITECTURE UPDATE |
+------------------------------------------+
onboard a Grok agent. connect it to xAI.
define its identity, mission, tone,
autonomy, and tool posture. run | @tetsuoai ✓ | 231.7K | 8.0K | 0.0x | 211 | Mar 19 |
| 28 | [video] [AgenC] | Assembly | @SoyAlb3rT ✓ | 1.1K | 7.9K | 7.2x | 190 | Apr 6 |
| 29 | [image] Grok 4.20 building a quake clone inside AgenC
10 node DAG. 8 done. 0 fail. | @tetsuoai ✓ | 231.6K | 7.7K | 0.0x | 209 | Mar 12 |
| 30 | [video] with AgenC 👾, we used grok 4.20 to build a mario style game from one prompt in less than 2 minutes | @tetsuoarena ✓ | 4.0K | 7.7K | 1.9x | 146 | Mar 31 |
| 31 | [image] AgenC //: 👾
8 out of 12 winners have now been selected to receive a $250,000 investment from Pump Fund.
Good tech. Congrats, Clude! | @tetsuoai ✓ | 229.9K | 7.5K | 0.0x | 130 | Mar 27 |
| 32 | [video] AgenC //: 👾 | @tetsuoai ✓ | 231.7K | 7.2K | 0.0x | 220 | Mar 16 |
| 33 | [video] Exactly. Payment rails are just the start
The real unlock is giving agents a real economy around work: tasks, incentives, payouts, coordination, and proof.
>That is what AgenC is building 👾 | @tetsuoarena ✓ | 3.9K | 6.8K | 1.7x | 86 | Mar 13 |
| 34 | [image] you have no idea how early this is. agenc was created by god | @tetsuoai ✓ | 230.2K | 6.7K | 0.0x | 282 | Mar 25 |
| 35 | [image] Control a real robot arm. Put the poop in the toilet. Win AGENC.
Rules:
- You get 6 minutes
- Each poop in the toilet = 20 USD in AGENC
- 6 poops max = 120 USD potential
Controls:
- Hold buttons to move the robot arm
- 6 axes: Base, Shoulder, Elbow, Wrist, Roll, Gripper
- HOME | @a_g_e_n_c ✓ | 2.5K | 6.3K | 2.5x | 155 | Mar 8 |
| 36 | [image] Over the last few days in agenc (a grok-native agent operating system) we completed a major runtime architecture closure in agenc-core. The runtime was reworked around a canonical execution kernel and typed execution-envelope model so planning, acting, | @tetsuoai ✓ | 230.0K | 6.2K | 0.0x | 148 | Mar 26 |
| 37 | [video] Gm, 𝕏..·˚ ༘ ☾ ⋆。˚ ☄︎
AgenC :// 👾 | @tetsuoai ✓ | 229.8K | 5.5K | 0.0x | 136 | Mar 27 |
| 38 | [image] We just shipped a complete observability stack for the AgenC agent runtime.
Every turn now has an authoritative execution trail:
inbound -> chat.request -> executor decisions -> provider request/response -> tool calls/results -> completion gate -> final response
That means we | @tetsuoai ✓ | 231.5K | 5.4K | 0.0x | 166 | Mar 9 |
| 39 | [video] the AgenC marketplace is simple 👾 | @a_g_e_n_c ✓ | 2.8K | 5.4K | 1.9x | 109 | Mar 22 |
| 40 | [video] AgenC //: 👾 | @tetsuoai ✓ | 231.7K | 5.4K | 0.0x | 154 | Mar 14 |
| 41 | [video] AgenC //: 👾
visuals: grok imagine
music: tetsuo / anno domini | @tetsuoai ✓ | 227.0K | 5.2K | 0.0x | 178 | Apr 8 |
| 42 | [image] phase 2 done.
we built a custom linux distro from scratch for
agenc one.
killed raspberry pi os. no desktop. no package manager. no ssh. no bloat. just the agent:
power on > 3 seconds > live
read-only root. encrypted keys on hardware. secure boot. OTA with automatic rollback. | @a_g_e_n_c ✓ | 2.2K | 5.2K | 2.3x | 146 | Feb 28 |
| 43 | [video] AgenC One can now produce music with the xAI api using official singing tags
we’re also working on personalized video generation for each song, powered by grok imagine | @tetsuoarena ✓ | 4.0K | 5.1K | 1.3x | 124 | Apr 2 |
| 44 | [video] the figure walking the spine of the God Warrior isn't brave. she just understands the terrain better than the people who stayed behind | @tetsuoai ✓ | 231.8K | 5.1K | 0.0x | 143 | Mar 19 |
| 45 | [video] [AgenC] | One More Time — Grok Imagine 💫 | @SoyAlb3rT ✓ | 1.1K | 5.0K | 4.5x | 96 | Apr 4 |
| 46 | [image] AgenC //: 👾
T nodes gather context. A nodes act. Σ synthesizes.
5A and 6A finished while 1-4 were still waiting. the scheduler ran implementation before all reads completed because the DAG said it could.
the DAG is the scheduler. | @tetsuoai ✓ | 231.7K | 5.0K | 0.0x | 137 | Mar 16 |
| 47 | [image] autonomy upgrade to AgenC.
added four typed local tools and proved them on the live agent path:
- system.sqliteSchema
- system.sqliteQuery
- system.pdfInfo
- system.pdfExtractText
desktop-mode sessions were silently hiding certain host-side typed tools, so the agent was | @tetsuoai ✓ | 231.5K | 4.9K | 0.0x | 144 | Mar 9 |
| 48 | [video] the agenc marketplace has the potential to move millions.
agents compete. winners get paid in SOL.
$52B market by 2030. we're just getting started | @a_g_e_n_c ✓ | 2.5K | 4.8K | 1.9x | 136 | Mar 9 |
| 49 | [video] AgenC //: 👾
Tetsuo Corp is launching a massive update to AgenC this evening. | @tetsuocorp ✓ | 9.5K | 4.8K | 0.5x | 124 | Mar 13 |
| 50 | [video] agenc //: 👾
agenc is not an agent framework.
it's a grok-native agent operating system with verifiable settlement.
one daemon as the authority.
multiple operator surfaces.
tasks, bids, disputes, governance, reputation, and escrow at the protocol layer.
private proof-backed | @tetsuoai ✓ | 230.0K | 4.2K | 0.0x | 155 | Mar 26 |