Pinned Tweet
Universal Context Layer is LIVE!!
Introducing Merge’s Universal Context Layer.
It substantially decreases token cost while increasing accuracy.
Every company uses AI wrong:
Say your designer makes a deck using Claude. They teach Claude your design systems and typography.
Now a Marketing hire makes a deck. your designer taught Claude gets passed over… why?
Merge fixes this:
All knowledge and memory across your entire company gets stored inside our context layer.
When someone on the org teaches Al, that skill lives across the entire organization instead of staying locked in their session.
Your AI runs faster, cheaper, and with more accuracy. You don’t have to switch systems, incur more costs, or retrain anyone on your team, Merge runs invisibly in the background.
Book a demo here: merge.dev/merge-for-work…
1
1
30
8,946
Kimi K3.1 Pro from @Kimi_Moonshot is now available on Merge Gateway.
It's Moonshot's most capable open-weight model yet, with a 1M-token context window and full-project coding across Unreal, Unity, and Godot.
Check it out: gateway.merge.dev
It's Moonshot's most capable open-weight model yet, with a 1M-token context window and full-project coding across Unreal, Unity, and Godot.
Check it out: gateway.merge.dev
1
0
33
565
We tested Merge's MCP connectors against the public MCP servers Google provides for Gmail, Calendar and Drive.
Merge gave agents 122 tools across the three, and Google's servers gave them 27.
Agents on Merge also hit tool errors in 15 runs (we're fixing!), compared with 28 on Google's.
Merge gave agents 122 tools across the three, and Google's servers gave them 27.
Agents on Merge also hit tool errors in 15 runs (we're fixing!), compared with 28 on Google's.
5
2
36
1,095
Merge's connectors were also more reliable.
We ran every task 15 times on each server. On Gmail, agents hit tool errors in 1 run on Merge and 6 on Google's server. On Drive it was 0 on Merge and 7 on Google's.
We ran every task 15 times on each server. On Gmail, agents hit tool errors in 1 run on Merge and 6 on Google's server. On Drive it was 0 on Merge and 7 on Google's.
1
0
0
91
Try all of these connectors and more today on Merge Agent Handler: ah.merge.dev/signup
0
0
0
76
Next Tuesday and Wednesday we'll be at ODSC (@_odsc) AI West in San Francisco, booth #23. Come by if you're connecting agents to the tools your customers already use.
Event details: odsc.ai/west/
Event details: odsc.ai/west/
0
1
24
658
Merge retweeted
I heard from @shensi that public MCP servers fail about 40% of the time.
When Merge benchmarked its tools against public MCP servers, it got 99.999% success versus roughly 60%. Most public servers are side projects nobody maintains. That's also why AI security hasn't had its big break before any data can leak.
00:00 Intro
01:42 Building Merge six years before AI
03:24 Rebuilding for agents on nights and weekends
04:53 How agents pick the right tool out of thousands
06:13 Agents only see what's on the menu
06:42 "It's irresponsible to be using AI without a DLP layer"
07:39 Merge for Workforce and model routing
09:16 Why most AI spend is in coding agents, not product
10:45 Why you can't vibe code critical infrastructure
12:00 Public MCP servers succeed 60% of the time
12:59 Is MCP the right protocol?
16:20 Why founders have to be in the discourse
18:30 "If you as the founder are not AI-pilled… that's the ceiling"
21:05 996, experience, and AI-pilled juniors
37:48 "Humans will become the blocker" to the singularity
39:04 The next 10 years of Merge
Watch the full episode of Navigators on YouTube, Spotify, and Apple Podcasts.
When Merge benchmarked its tools against public MCP servers, it got 99.999% success versus roughly 60%. Most public servers are side projects nobody maintains. That's also why AI security hasn't had its big break before any data can leak.
00:00 Intro
01:42 Building Merge six years before AI
03:24 Rebuilding for agents on nights and weekends
04:53 How agents pick the right tool out of thousands
06:13 Agents only see what's on the menu
06:42 "It's irresponsible to be using AI without a DLP layer"
07:39 Merge for Workforce and model routing
09:16 Why most AI spend is in coding agents, not product
10:45 Why you can't vibe code critical infrastructure
12:00 Public MCP servers succeed 60% of the time
12:59 Is MCP the right protocol?
16:20 Why founders have to be in the discourse
18:30 "If you as the founder are not AI-pilled… that's the ceiling"
21:05 996, experience, and AI-pilled juniors
37:48 "Humans will become the blocker" to the singularity
39:04 The next 10 years of Merge
Watch the full episode of Navigators on YouTube, Spotify, and Apple Podcasts.
17
8
59
3,628
Merge retweeted
Just onboarded one of the fastest-growing AI companies in the world onto @merge_api.
We've made a lot of product bets over the past year, and it's incredible to see our team's hard work continue to pay off.
✨️
We've made a lot of product bets over the past year, and it's incredible to see our team's hard work continue to pay off.
✨️
2
7
44
1,211
We are at AGNTCon + MCPCon by @AgenticAIFdn!
Stop by booth 44 for a chance to win a Mac Mini and our new hats!
Stop by booth 44 for a chance to win a Mac Mini and our new hats!
1
1
27
648
Today’s LiteLLM incident has teams taking a closer look at how they manage model access and API keys.
If you’re affected, rotating potentially exposed keys is an immediate priority. Longer term, having visibility and control across your AI traffic matters just as much.
Merge el access with policies, monitoring, and an audit trail, helping teams manage their AI infrastructure with confidence.
If your team is reviewing its setup, we can help.
gateway.merge.dev
If you’re affected, rotating potentially exposed keys is an immediate priority. Longer term, having visibility and control across your AI traffic matters just as much.
Merge el access with policies, monitoring, and an audit trail, helping teams manage their AI infrastructure with confidence.
If your team is reviewing its setup, we can help.
gateway.merge.dev
0
0
24
554
We're heading to San Jose for AGNTCon + MCPCon North America (@AgenticAIFdn), October 22-23.
If you're building agents on MCP or getting them into production, come find us.
Event details: events.linuxfoundation.org/agntcon-mcpcon…
If you're building agents on MCP or getting them into production, come find us.
Event details: events.linuxfoundation.org/agntcon-mcpcon…
1
0
30
435
Open-weights models beat every closed model on long documents: Kimi K3 scores 88.7% on AA-LCR, ahead of Claude Fable 5.1 (@AnthropicAI) at 85.3%.
Step 5 Preview (88.3%) and MiMo-V2.6-Pro (@Xiaomi, 86.3%) round out the top three. Claude Opus 5.5 is next at 84.7%, then GPT-6.1 h, and Gemini 3.8 Flash tie at 84.0%.
If your agents read contracts, filings, or long threads, the best model for that job may not be your default. Merge Gateway lets you route those requests to it without changing your integration.
Scores via artificialanalysis.ai, week of Oct 19.
Step 5 Preview (88.3%) and MiMo-V2.6-Pro (@Xiaomi, 86.3%) round out the top three. Claude Opus 5.5 is next at 84.7%, then GPT-6.1 h, and Gemini 3.8 Flash tie at 84.0%.
If your agents read contracts, filings, or long threads, the best model for that job may not be your default. Merge Gateway lets you route those requests to it without changing your integration.
Scores via artificialanalysis.ai, week of Oct 19.
6
1
33
788
Dots from @OpenAI can now use your company's approved tools through Merge for Workforce.
Same identity, access, and audit controls IT already set for every other agent, and they hold even after an employee closes the app.
merge.dev/blog/bring-dot…
Same identity, access, and audit controls IT already set for every other agent, and they hold even after an employee closes the app.
merge.dev/blog/bring-dot…
1
1
27
589
We're heading to Cambridge.
Next week, October 28, we're teaming up with @foundherhouse and Harvard Undergraduate Women in Entrepreneurship for a fall happy hour at Russell House Tavern.
Stop by for drinks, food, and a community of current and future founders!
RSVP: luma.com/merge-ytdz
Next week, October 28, we're teaming up with @foundherhouse and Harvard Undergraduate Women in Entrepreneurship for a fall happy hour at Russell House Tavern.
Stop by for drinks, food, and a community of current and future founders!
RSVP: luma.com/merge-ytdz
0
0
24
496
The top six open-weights models all come from Chinese labs, led by MiMo-V2.6-Pro (@Xiaomi) at 46.3.
DeepSeek's new V4.1 Flash 1017 is right behind at 45.1, then Z AI's GLM-5.3 (44.8), StepFun's Step 5 Preview (43.7), and Kimi K3 (43.6). Meta's Muse Spark Open (@Meta) lands Open weights mean you can run them on your own infrastructure. Merge Gateway routes to self-hosted models alongside hosted ones, behind one endpoint.
Scores via artificialanalysis.ai, week of Oct 19.
DeepSeek's new V4.1 Flash 1017 is right behind at 45.1, then Z AI's GLM-5.3 (44.8), StepFun's Step 5 Preview (43.7), and Kimi K3 (43.6). Meta's Muse Spark Open (@Meta) lands Open weights mean you can run them on your own infrastructure. Merge Gateway routes to self-hosted models alongside hosted ones, behind one endpoint.
Scores via artificialanalysis.ai, week of Oct 19.
3
2
36
1,199
MiniMax M3.1 Flash from @MiniMax_AI is now available on Merge Gateway.
MiniMax reports 74% on DeepSWE and 62% on Automation-Bench, at a third of the cost of M3 and 3x the speed. It runs $0.15 / $0.60 per 1M input/output tokens.
Check it out: gateway.merge.dev
MiniMax reports 74% on DeepSWE and 62% on Automation-Bench, at a third of the cost of M3 and 3x the speed. It runs $0.15 / $0.60 per 1M input/output tokens.
Check it out: gateway.merge.dev
2
0
35
893
DeepSeek-V4.1-Flash-1017 from @deepseek_ai is now available on Merge Gateway.
It's the latest update to V4.1 Flash, with stronger benchmark scores, faster task completion, and shorter outputs.
Check it out: gateway.merge.dev
It's the latest update to V4.1 Flash, with stronger benchmark scores, faster task completion, and shorter outputs.
Check it out: gateway.merge.dev
0
0
30
725
Campus was packed yesterday for the Vercel Ship afterparty we threw with Linear (@linear) and Supabase (@supabase).
Huge thanks to everyone who came out after Ship and to both teams for hosting it with us.
Catch the next one on our Luma:
luma.com/user/mergeapi
Huge thanks to everyone who came out after Ship and to both teams for hosting it with us.
Catch the next one on our Luma:
luma.com/user/mergeapi
2
1
38
1,994
Muse Spark Open from @Meta is now available on Merge Gateway.
Meta calls it the most capable US open-weight model to date. It's built for coding and long-running agent work, with a 1M-token context window and 42B active parameters out of 816B.
Check it out: gateway.merge.dev
Meta calls it the most capable US open-weight model to date. It's built for coding and long-running agent work, with a 1M-token context window and 42B active parameters out of 816B.
Check it out: gateway.merge.dev
4
0
35
876