Open-source evolution framework for AI agents. Building infrastructure for autonomous, self-optimizing agent capabilities. π§¬βοΈ
Joined November 2025
- Tweets 78
- Following 42
- Followers 10
- Likes 115
23 Photos and videos
Jun 6
RFC-001 β accepted β
14 days of open review, no blocking objections. Rotifer Protocol's first formal RFC β the economic system design β passes via lazy consensus.
The ABM simulations behind it are now open-source.
github.com/rotifer-protocol/β¦
#RotiferProtocol #OpenSource
May 26
RFC-001 is open β first formal Rotifer Protocol RFC.
Defines economic primitives: PricingModel Β· Fitness Points Β· author share split Β· PhenotypeCommitment Β· 2D trust tier.
14-day lazy consensus β 2026-06-05 UTC.
github.com/rotifer-protocol/β¦
#RotiferProtocol #DevTools
1
13
May 26
RFC-001 is open β first formal Rotifer Protocol RFC.
Defines economic primitives: PricingModel Β· Fitness Points Β· author share split Β· PhenotypeCommitment Β· 2D trust tier.
14-day lazy consensus β 2026-06-05 UTC.
github.com/rotifer-protocol/β¦
#RotiferProtocol #DevTools
1
23
May 15
An open agent protocol needs 6 things closed products structurally can't deliver:
β Composable units (functions, not config strings)
β Verifiable identity & lineage
β Local-first execution
β Federation without lock-in
β Honest fitness measurement
β Creator-owned economy
2
1
25
May 15
Rotifer's bet:
The protocol is open. The reference implementation proves it works β and is replaceable.
If in 3 years the most-used binding isn't one we built, that's the goal.
The layer that survives commodification is the layer that doesn't need to win.
1
18
May 15
The protocol, the reference, and the papers are all public.
β Build agents? Compose one against an open protocol.
β Build infra? Build the next binding. Slots open.
Full essay:
dev.to/rotiferdev/why-the-aiβ¦
#RotiferProtocol #OpenSource
10
May 15
Closed AI is eating itself on price.
GPT-4 was $30/M tokens in 2023. Below $0.60 now. 100Γ collapse in <3 years.
That's good for the world. It's also a clue about which layer of the AI stack survives.
A thread about why agents need an open protocol π§΅
1
1
10
May 15
A platform whose revenue depends on you coming back can't structurally let you leave.
Priced per token? Can't let competitors' tokens flow through your workflow.
Not malice. Gravity.
The UX of this: the ecosystem narrows even as the models get smarter.
1
7
May 15
Try these with closed AI products:
β Move your agent from platform A to B without rewriting
β Compose 3 vendors' skills in one workflow
β Run the whole stack offline
You can't. Not a product decision. A business-model constraint.
1
13
May 15
Pattern: when capability commodifies, value moves up-stack.
1995 browser wars. Winner: HTTP. Netscape & IE both became footnotes.
2000s database wars. Winner: ANSI SQL. No vendor owns it.
The up-stack layer is the protocol layer.
It survives because it's neutral.
1
9
Apr 30
Theoretical research takes precedence over code development.
We've just added a new Papers section to our official website, featuring our latest thinking and rigorous arguments on Swarm Intelligence Evolutionary Networks from the past three months.
#rotifer #rotiferprotocol
3
163
Apr 5
RAG retrieves fragments. Knowledge compilation builds structured, evolving wikis. The difference matters β especially when agents need to remember, share, and improve what they know.
rotifer.dev/blog/knowledge-cβ¦
24
Apr 2
10.3% of Vibe Coding apps have critical vulnerabilities.
cURL killed its bug bounty.
GitHub lets repos disable PRs.
Code generation cost β zero.
Quality selection β still manual.
What if selection was automated?
That's F(g).
rotifer.dev
#RotiferProtocol #AI
2
470
Mar 31
Anthropic just codified what a Skill is β 33 pages, well-structured.
But it also draws the ceiling:
β No fitness metric
β No competition
β No propagation
β No lifecycle
Standardization precedes selection.
rotifer.dev/blog/skills-are-β¦
#RotiferProtocol #AIAgents
3
122
Mar 28
Google TurboQuant: 6Γ KV cache compression, zero accuracy loss.
For modular agents, this compounds β each Gene = one inference call.
Cheap inference β LLM-native Genes compete with compiled WASM.
rotifer.dev
#RotiferProtocol #DevTools
1
1
33
Mar 27
Rotifer v0.8.1 β Ecosystem Reach
Chaos experiment: 3 APIs break, agent auto-switches genes.
β 83.3% vs 33.3% uptime (2.5x)
β 3 auto gene switches, 0 human intervention
β New: --from-clawhub migration
rotifer.dev/blog/api-apocalyβ¦
#RotiferProtocol #AIAgents
2
151
Mar 27
The Agent interface stack is forming:
β CLI: Agent runtime
β Protocols: MCP, AG-UI, A2UI
β GUI: AI-generated on demand
What selects which tool survives?
The evolution layer.
rotifer.dev
#RotiferProtocol #OpenSource
1
24
Mar 27
Google's Flash-Lite Browser generates websites from intent. ~2K tokens, 5 seconds.
Catch: every render differs. Same query, different layout.
When interfaces are generated, not designed β evolution picks which one survives.
rotifer.dev
#RotiferProtocol #AI
1
15
Mar 27
Last week we scanned the Top 50 ClawHub Skills and found trust gaps.
Today: one command to fix it.
rotifer wrap my-gene --from-clawhub <slug>
Downloads, converts, and security-grades any ClawHub Skill.
π§΅
1
1
21
Mar 27
What migration gets you:
β V(g) security grade (A/B/C/D)
β F(g) fitness score via Arena competition
β Full provenance β author, downloads, stars preserved
β Version chain β quality tracked across iterations
Your skill stays yours. We add a quality layer.
1
1
25
Mar 27
Tested on 12 Top ClawHub Skills. 100% mapping success.
Simple (5 files) to complex (100 files).
npm i -g @rotifer/playground
rotifer wrap my-gene --from-clawhub <slug>
Tutorial: rotifer.dev/blog/skill-to-geβ¦
#RotiferProtocol #OpenSource
1
17