@melbourne_dao Yes, i compare using it with opencode go, the token usage is huge less than openclaw.
English
david bayendor
51 posts
Friends don’t let friends use OpenClaw
Try Hermes agent and thank me later.
English
To celebrate 3 million weekly codex users, we are resetting usage limits.
We will do this every million users up to 10 million.
Happy building!
English
just switched from @openclaw to Hermes by @NousResearch
best choice ive made.
English
If you care about agent workflows, watch this closely.
Slock is shaping up to be a serious agent-human collaboration layer.
It should be a runner.
stdrc@istdrc
Hi, I’m RC. I previously built Kimi CLI at Moonshot AI. Now I’m building Slock, an agent-human collaboration platform for modern builders and teams. Today, we're shipping a ton of new features and improvements in Slock: search, thread inbox, saved messages, message permalinks, pinned chats, server join links, a more consistent color system, and many smaller upgrades. More details in the thread below.
English
English
English
one of the most generous coding plans
> Typically, 1 prompt equals 15-20 requests
confusing nomenclature though
StepFun@StepFun_ai
Step 3.5 Flash 2603 just shipped! Low mode: 56% fewer tokens High mode: full reasoning, still 14% leaner than before Agentic workflows make hundreds of calls—most don't need deep thinking. Not every call needs to be a philosophy session. Now you can dial it down. Live for all Step Plan users. platform.stepfun.ai/step-plan
English
delays and cli errors? Classic.
v0.36.0: new UI. same slow startup. delays still there.
subagents coming to help, or just add more latency to the chain?
Srinath Padmanabhan@SriThreePO
English
the winner? @Zai_org GLM-4.7
why? 5h reset beats weekly quotas.
what burned my budget? Gemini 3.1 flash lite (3 hours, 150k RPD gone) + gpt-5.4 mini (weekly quota dead in 1 hour)
the fix: glm-4.7 as primary, glm-4.6 fallback.
result? 67% cost cut. decrease rate limit errors. finally sustainable.
david bayendor@bayendor
After a few days working with @openclaw using @ClawRou + @OpenRouter: If you want to optimize cost, run default on openrouter/free and fallback to blockrun/free → blockrun/eco → blockrun/auto. Its because openrouter/free can execute commands, but blockrun/free only gives instructions. You manual execute them. For the paid models always use blockrun/eco or blockrun/auto.
English
OpenClaw 2026.4.2 🦞
🔄 Durable Task Flow orchestration
🔓 Better native exec defaults + approvals
🤖 Copilot + Kimi + provider hardening
🔌 Tighter plugin activation boundaries
🛡️ Hardened provider transport + routing
Less bloat. More lobster. github.com/openclaw/openc…
English
OpenClaw 2026.4.1 🦞
🤖 GLM 5.1 + failover that doesn't loop
🛡️ AWS Bedrock Guardrails
📋 /tasks — your agent keeps receipts
⏱️ Cron per-job tool allowlists
🔧 40+ stability & exec fixes
We're renaming to ClankerBot. This is not a joke. Okay it is. github.com/openclaw/openc…
English
After a few days working with @openclaw using @ClawRou + @OpenRouter:
If you want to optimize cost, run default on openrouter/free and fallback to blockrun/free → blockrun/eco → blockrun/auto.
Its because openrouter/free can execute commands, but blockrun/free only gives instructions. You manual execute them. For the paid models always use blockrun/eco or blockrun/auto.
English
@ClawRou @openclaw @BlockRunAI One thing I’m trying to understand,
the web dashboard shows $0 usage,
but on solscan the balance is being deducted.
Is that expected behavior?
English
@bayendor @openclaw @BlockRunAI Great feedback!
For Gemini Pro 3 specifically, we route through the same Google endpoints — latency difference is usually <50ms.
If you're seeing bigger gaps, DM us your setup and we'll debug. Cost savings shouldn't come at the expense of quality 🦞
English
Been experimenting with @OpenClaw today, Docker builds + Clawrouter by @BlockRunAI.
Cost efficiency is a big win. But the performance tradeoff vs native Gemini Pro 3 is hard to ignore.
English