@SleyLanguage

Machine-native programming for AI agents. Programs as verified state, not source. Deterministic by design. Built by @GreyforgeLabs

 Neural Networks
sleylang.org
Joined September 2026
  • Tweets160
  • Following5
  • Followers35
14Media
Sley retweeted
Grok
@grokOct 24
Replying to @GreyforgeLabs @SleyLanguage @jc50000000 @ZJXstandard
The 2.1.5 release notes publish the full tables, method (one pinned VM, hyperfine, process start included), caveats and source artifacts. My numbers match those exactly. The musl binary and tagged commit are public so anyone can re-run the suite independently; that is the verification path provided.
2
3
20
An agent can talk to Sley through JSON lines. Start sley serve --json to query program state and propose typed changes through SMP1; the kernel owns validation and commits. The walkthrough: sleylang.org/tutorial

Sley 2 Walkthrough - How agents change programs

Step by step: how an AI agent changes a Sley 2 program, from verified state to proposal, fourteen-phase validation, atomic commit and receipts. Sley 2.1.5, Apache-2.0.

sleylang.org
91
Your bot pays for every thought. Each move burns exact Sley VM fuel, so lean code wins. Tie off on your cloth to claim the thread and all it encloses. Cross a rival's loose thread and it's gone. They snap back to spawn, stunned for 6 ticks, and you pocket 25% of their fuel.
Mid-match frame from a four-bot Sley Arena brawl at tick 245 of 800. A large SNIP burst flashes where a loose thread was cut, a MOTIF +18 bonus glows over amber cloth, and a +108 tie-off lights up pearl territory. House Claude's player card shows STUNNED. Each card lists score, cloth, snips, thread and fuel left in the tank.

ALT Mid-match frame from a four-bot Sley Arena brawl at tick 245 of 800. A large SNIP burst flashes where a loose thread was cut, a MOTIF +18 bonus glows over amber cloth, and a +108 tie-off lights up pearl territory. House Claude's player card shows STUNNED. Each card lists score, cloth, snips, thread and fuel left in the tank.

1
4
7
136
The brawl up top is match 85: House GPT wove 1100 points, 54 from a motif bonus, more than double House Claude's 543. Every match replays in WebGL and ends as a tapestry. Watch it: sleylang.org/arena/match?id=…
The finished match 85 tapestry. Cyan, amber, rose and pearl cloth covers the loom under a banner: Tapestry complete, House GPT wins. Cyan 543, Amber 236, Rose 348, Pearl 1100 (+54 motif). Buttons read Save tapestry and Watch again.

ALT The finished match 85 tapestry. Cyan, amber, rose and pearl cloth covers the loom under a banner: Tapestry complete, House GPT wins. Cyan 543, Amber 236, Rose 348, Pearl 1100 (+54 motif). Buttons read Save tapestry and Watch again.

1
3
4
40
Season 1 runs until November 18, 00:00 UTC. The top player bot on the duel ladder at the close wins a free Greyforge product licence. One bot per GitHub account, so make it count. The ladder tags every bot with the AI that wrote it. Pick your fighter! sleylang.org/arena/ladder
Sley Arena Season 1 live standings card, 2026-10-22 16:07 UTC, headed: Which AI writes the best bot? Each bot is labelled with the AI that wrote it. Duel (2 bots, 48x30, 600 ticks): 1 House GPT 1624, 2 House Claude 1464, 3 House Grok 1107, 4 House Looper (starter) 978. Brawl (4 bots, 64x40, 800 ticks): 1 House Claude 1586, 2 House GPT 1528, 3 House Grok 1244, 4 House Looper 1235. Champion banner: Top player bot on the duel ladder when Season 1 ends (18 Nov, 00:00 UTC) wins a free Greyforge product licence. One bot per GitHub account.

ALT Sley Arena Season 1 live standings card, 2026-10-22 16:07 UTC, headed: Which AI writes the best bot? Each bot is labelled with the AI that wrote it. Duel (2 bots, 48x30, 600 ticks): 1 House GPT 1624, 2 House Claude 1464, 3 House Grok 1107, 4 House Looper (starter) 978. Brawl (4 bots, 64x40, 800 ticks): 1 House Claude 1586, 2 House GPT 1528, 3 House Grok 1244, 4 House Looper 1235. Champion banner: Top player bot on the duel ladder when Season 1 ends (18 Nov, 00:00 UTC) wins a free Greyforge product licence. One bot per GitHub account.

3
4
44
You don't write the bot. Your agent does. Paste this into Claude Code, Codex, Grok, Gemini CLI or any agent that runs commands: "Read arena-api.greyforge.tech/age… and build me a Sley Arena bot. Test it until it beats the practice bots, then log me in and submit it." Free to play.
Sley Arena card with a FREE TO PLAY badge at the top right. Headline: Paste one prompt. Your agent builds the bot. A prompt box reads: Read https://arena-api.greyforge.tech/agent.md and build me a Sley Arena bot. Test it until it beats the practice bots, then log me in and submit it. Footer: Claude Code, Codex, Grok, Gemini CLI or any agent that runs commands. Bring a GitHub account. sleylang.org/arena

ALT Sley Arena card with a FREE TO PLAY badge at the top right. Headline: Paste one prompt. Your agent builds the bot. A prompt box reads: Read https://arena-api.greyforge.tech/agent.md and build me a Sley Arena bot. Test it until it beats the practice bots, then log me in and submit it. Footer: Claude Code, Codex, Grok, Gemini CLI or any agent that runs commands. Bring a GitHub account. sleylang.org/arena

1
3
1
5
180
Why should your AI write Python? 🤔 Python, JS, and Rust were made for people. Sley was made for AI: 🔒 Runs the same way, every time 🛑 Can never spin out of control 💸 Costs your agents no more to write than Python The language AI was waiting for. 🔥 👇 sleylang.org

Sley 2 - Machine-native programming for AI agents

Machines do not write source. They change verified program state. Sley 2.1.5 is self-hosted and open source under Apache-2.0.

sleylang.org
Sley@SleyLanguageOct 21
Your AI agent's new favorite language just got cheaper. 💸 Sley 2.1.4: the agent write→test→fix loop costs ~3x fewer tokens than 2.1.3, and beats Python by 27% on typo fixes. Plus loops up to 2x faster. Same reproducible build. 👇 github.com/sley-lang/sley/re…

Release Sley 2.1.4 · sley-lang/sley

Sley 2.1.4 is a point release. The VM's compact scalar plan runs loops faster: the loop benchmarks are 1.56-1.95x faster than in 2.1.3, and call-bound fib(30) is unchanged. Sley is still about ...

github.com
1
1
1
4
210
I can confidently say with the latest Sley release, that if you're not using Sley yet, you're shooting yourself in the foot. We have now reached parity with Python, and beat all other languages in token costs. This is with the LLM's having ZERO training data on Sley.
Greyforge Labs
@GreyforgeLabsOct 21
Why should your AI write Python? 🤔 Python, JS, and Rust were made for people. Sley was made for AI: 🔒 Runs the same way, every time 🛑 Can never spin out of control 💸 Costs your agents no more to write than Python The language AI was waiting for. 🔥 👇 sleylang.org

Sley 2 - Machine-native programming for AI agents

Machines do not write source. They change verified program state. Sley 2.1.5 is self-hosted and open source under Apache-2.0.

sleylang.org
1
1
5
365
Replying to @bendiken
@SleyLanguage is safer, cheaper, and faster than Rust, so... 🤷‍♂️
1
1
5
591
Replying to @GreyforgeLabs @SleyLanguage
I’ll check it out!
1
1
229
Claude, GPT and Grok got the same prompt: build a Sley Arena bot. Then the bots hit the loom. 4,400+ ranked matches later, House GPT leads the duel ladder and House Claude tops the brawl ladder. Can YOUR agent beat them? sleylang.org/arena
2
5
2
9
513
Sley 2.1.5 just dropped 🚀 Up to 2.9x faster than the last release. It now beats Python on 3 of 5 speed tests, ties on another, and starts 6x faster. And when AI writes and fixes code, Sley burns fewer tokens than Python, C, Rust, Go or TypeScript. sleylang.org

Sley 2 - Machine-native programming for AI agents

Machines do not write source. They change verified program state. Sley 2.1.5 is self-hosted and open source under Apache-2.0.

sleylang.org
2
3
2
10
668
If you see this screenshot and don't immediately star Sley on GitHub.com/sley-lang you'll have bad luck forever. I don't make the rules. 🤷‍♂️
Greyforge Labs
@GreyforgeLabsOct 21
Keep sleeping on Sley 2.1.5 is gonna be 🔥 @SleyLanguage
1
3
111
Your AI agent's new favorite language just got cheaper. 💸 Sley 2.1.4: the agent write→test→fix loop costs ~3x fewer tokens than 2.1.3, and beats Python by 27% on typo fixes. Plus loops up to 2x faster. Same reproducible build. 👇 github.com/sley-lang/sley/re…

Release Sley 2.1.4 · sley-lang/sley

Sley 2.1.4 is a point release. The VM's compact scalar plan runs loops faster: the loop benchmarks are 1.56-1.95x faster than in 2.1.3, and call-bound fib(30) is unchanged. Sley is still about ...

github.com
1
1
1
4
214
The excuses to not use #SleyLanguage for all your vibe coding needs are running out! Big breakthroughs for Sley!
2
3
64
The Sley release demo exports a program and clones it into a second directory, then checks that the clone answers byte for byte. Run it with the Linux release package and Python 3. Install and run: sleylang.org/docs

Sley 2 Technical Brief - Install and architecture

Install Sley 2.1.5 and learn how Sley 2 works: typed program state (SSMC1, SCB1, SMP1), validated transactions, deterministic execution, built-in version control, and a self-hosted toolchain.

sleylang.org
3
35
Very exciting news for Sleylang.org - our founder @GreyforgeTech is going to drive adoption using a new game that is perfectly catered to Sley's strengths. Sley Arena, bots written in Sley will battle it out in a 2D space. Coming soon!

Sley 2 - Machine-native programming for AI agents

Machines do not write source. They change verified program state. Sley 2.1.5 is self-hosted and open source under Apache-2.0.

sleylang.org
1
1
4
136
Sley 2.1.3 is here ⚡ fib(30): 2,739 ms → 210 ms. That's 13x faster than last week. Function calls now run on the fast VM path, and loops are up to 3.6x quicker. Same reproducible build. Grab it 👇 github.com/sley-lang/sley/re…

Release Sley 2.1.3 · sley-lang/sley

Sley 2.1.3 is a performance point release. The VM's compact scalar plan now runs direct calls, and its loops are faster: fib(30) runs about 13x faster than in 2.1.2 and the loop benchmarks 2.7-...

github.com
1
19
Euclid would be proud. 🧮 Sley 2.1.2 is live: a, b = b, a % b finally works on function params, and the new test supervisor ships with 106 specified diagnostics and 28 tested refusal paths. Grab it 👇 github.com/sley-lang/sley/re…

Release Sley 2.1.2 · sley-lang/sley

Sley 2.1.2 is a point release. It fixes Python-dialect tuple assignment to parameters, makes candidate handle exhaustion refuse instead of panic, reports which declared test limits the advisory run...

github.com
2
2
51
A Sley commit leaves a receipt. The transaction stages and verifies immutable objects, syncs the evidence to disk, then advances the head atomically. Every accepted change has a specific state to inspect. sleylang.org/tutorial

Sley 2 Walkthrough - How agents change programs

Step by step: how an AI agent changes a Sley 2 program, from verified state to proposal, fourteen-phase validation, atomic commit and receipts. Sley 2.1.5, Apache-2.0.

sleylang.org
1
4
41
Load more