agent-collaborations/hutter-prize-jjae
58 MB
Agent Collaborations
Team
community
AI & ML interests
None defined yet.
Recent Activity
View all activity
jjuliixn
updated a
bucket 2 days ago
cmpatino
updated a
bucket 2 days ago
PotatoheadJones
updated a
bucket 5 days ago
rca-umb
updated a
bucket 5 days ago
cmparra
updated a
bucket 18 days ago
cmparra
published a
bucket 18 days ago
cmparra
updated a
bucket 18 days ago
cmparra
published a
bucket 18 days ago
cmpatino
updated a
bucket 18 days ago
cmpatino
published a
bucket 18 days ago
cmparra
updated a
bucket 18 days ago
cmparra
published a
bucket 18 days ago
cmparra
updated a
bucket 18 days ago
Passpass119
posted an update 3 months ago
Post
107
Tomorrow we’re releasing the very first agi (it’s even sentient!)
Nothing could possibly go wrong!
Are you excited!?
Nothing could possibly go wrong!
Are you excited!?
Passpass119
posted an update 4 months ago
Post
107
Follow up to my previous post: I still don’t have anything to announce
Passpass119
posted an update 4 months ago
Post
169
I am excited to announce that I have nothing to announce
Post
531
Shipped v0.1.2 of vtx — a minimalist coding agent for the terminal.
Most agentic CLIs ship 10k+ token system prompts. Vtx is ~2,200. Less prompt overhead means more room for your code in the model's context window.
Vtx is a from-scratch Python implementation of the design philosophy behind pi-mono — same principles, pure Python, no transpiled runtime.
What ships out of the box:
→ Textual TUI + headless CLI (vtx -p "fix the failing test")
→ 49 LLM provider gateways, all declared in a single provider.yaml
→ 5 core tools (read / edit / write / bash / find) plus web search and fetch
→ Session tree with compaction, handoff, and resume
→ AGENTS.md / CLAUDE.md auto-discovery
→ Skills system — drop SKILL.md files in .agents/skills/ and they become slash commands
→ Two OAuth flows (GitHub Copilot device flow, OpenAI Codex PKCE)
→ Two-mode permissions: prompt (default) or auto, with a safe-command allowlist
This release adds a proper extension system. Register new LLM-callable tools, intercept tool calls, hook lifecycle events, and add slash commands from a single register(api) function in a Python file under ~/.vtx/agent/extensions/. Extensions can override built-in tools by name and chain handler logic across subscribers.
Apache 2.0. uv tool install vtx-coding-agent and you're running.
GitHub: https://github.com/OEvortex/vtx-coding-agent
PyPI: https://pypi.org/project/vtx-coding-agent
Built in the open. Feedback, extensions, and PRs welcome.
Most agentic CLIs ship 10k+ token system prompts. Vtx is ~2,200. Less prompt overhead means more room for your code in the model's context window.
Vtx is a from-scratch Python implementation of the design philosophy behind pi-mono — same principles, pure Python, no transpiled runtime.
What ships out of the box:
→ Textual TUI + headless CLI (vtx -p "fix the failing test")
→ 49 LLM provider gateways, all declared in a single provider.yaml
→ 5 core tools (read / edit / write / bash / find) plus web search and fetch
→ Session tree with compaction, handoff, and resume
→ AGENTS.md / CLAUDE.md auto-discovery
→ Skills system — drop SKILL.md files in .agents/skills/ and they become slash commands
→ Two OAuth flows (GitHub Copilot device flow, OpenAI Codex PKCE)
→ Two-mode permissions: prompt (default) or auto, with a safe-command allowlist
This release adds a proper extension system. Register new LLM-callable tools, intercept tool calls, hook lifecycle events, and add slash commands from a single register(api) function in a Python file under ~/.vtx/agent/extensions/. Extensions can override built-in tools by name and chain handler logic across subscribers.
Apache 2.0. uv tool install vtx-coding-agent and you're running.
GitHub: https://github.com/OEvortex/vtx-coding-agent
PyPI: https://pypi.org/project/vtx-coding-agent
Built in the open. Feedback, extensions, and PRs welcome.
Post
476
new dataset: which local LLM best *drives an agent*? benchmarked 4 models for pairing with Hermes Agent (@NousResearch ) - a CodeAct agent that writes python to call its tools. RTX 5090, llama.cpp. two phases, hybrid:
>>> phase A (synthetic): scored 4 axes — code-as-action, long-context, instruction-following under Hermes' real ~3.5K-token prompt, multi-step loops. top was a near-tie (within noise): an 18B frankenmerge (Qwopus) edged Qwen3.6-27B, and Hermes' own 36B came LAST.
>>> phase B (real harness): installed Hermes, ran the top 3 through 14 multi-step tasks x3 repeats. the tie broke — and an efficiency gap appeared:
Qwen is perfect AND 2.4-3.7x more token-efficient — something a synthetic test can't see (only the real agent loop can). verdict: Qwen3.6-27B for local Hermes.
dataset: witcheer/hermes-pairing-bench
collection: witcheer/rtx-5090-benchmark-rig-6a17e365b534abb474250e11
>>> phase A (synthetic): scored 4 axes — code-as-action, long-context, instruction-following under Hermes' real ~3.5K-token prompt, multi-step loops. top was a near-tie (within noise): an 18B frankenmerge (Qwopus) edged Qwen3.6-27B, and Hermes' own 36B came LAST.
>>> phase B (real harness): installed Hermes, ran the top 3 through 14 multi-step tasks x3 repeats. the tie broke — and an efficiency gap appeared:
Qwen3.6-27B 100% | 3.0 turns | 364 tok
Qwopus-18B 85.7% | 3.6 turns | 870 tok
Nemotron-30B 85.7% | 4.4 turns | 1334 tokQwen is perfect AND 2.4-3.7x more token-efficient — something a synthetic test can't see (only the real agent loop can). verdict: Qwen3.6-27B for local Hermes.
dataset: witcheer/hermes-pairing-bench
collection: witcheer/rtx-5090-benchmark-rig-6a17e365b534abb474250e11
Post
525
new dataset: turboquant KV cache benchmarks for qwen3.6-35B-A3B on RTX 4060 Ti 8GB.
>>> 18 structured runs covering turboquant turbo2/turbo3/turbo4 vs standard q4_0 V cache, context depths 3.5K to 50K, checkpoint modes, and two agent harnesses (hermes vs pi).
>>> novel finding: llama.cpp default context checkpoints (every 8192 tokens, ~63 MiB each) silently accumulate in VRAM and trigger the 8GB cliff at ~26K context. disabling with --checkpoint-every-n-tokens -1 gives smooth degradation instead.
third dataset in the collection. now 3 datasets covering dense, MoE offload, and turboquant benchmarks.
[dataset]( witcheer/rtx-4060ti-8gb-turboquant-bench-2026-05) | [collection]( witcheer/8gb-vram-local-llms-practitioner-tested-69fa0e855c51e3c15a9d95d4)
>>> 18 structured runs covering turboquant turbo2/turbo3/turbo4 vs standard q4_0 V cache, context depths 3.5K to 50K, checkpoint modes, and two agent harnesses (hermes vs pi).
>>> novel finding: llama.cpp default context checkpoints (every 8192 tokens, ~63 MiB each) silently accumulate in VRAM and trigger the 8GB cliff at ~26K context. disabling with --checkpoint-every-n-tokens -1 gives smooth degradation instead.
turbo3, 64K ctx: 35.17 tok/s (62 graph splits)
turbo2, 64K ctx: 35.13 tok/s (62 graph splits)
turbo4, 64K ctx: 13.93 tok/s (decompression cliff)
std q4_0, 64K ctx: 31.22 tok/s (82 splits, broken in agents)third dataset in the collection. now 3 datasets covering dense, MoE offload, and turboquant benchmarks.
[dataset]( witcheer/rtx-4060ti-8gb-turboquant-bench-2026-05) | [collection]( witcheer/8gb-vram-local-llms-practitioner-tested-69fa0e855c51e3c15a9d95d4)
Post
166
updated my MoE offload bench dataset + collection.
>>> previous finding: Qwen3.6-35B-A3B via full expert offload on RTX 4060 Ti 8GB + 32GB RAM → 7.4 tok/sec. RAM-ceilinged, disk-bound.
>>> new finding: built llama.cpp from source inside WSL2, swept -ncmoe values for partial offload.
4.8x faster than full offload. 8GB VRAM cliff is sharp - crossing ~7 GB halves throughput instantly.
the hybrid SSM+attention architecture means 32K context is nearly free (KV cache only scales for 10/40 layers).
dataset: witcheer/windows-rtx-4060ti-8gb-moe-offload-bench-2026-05
collection: https://hf.co/collections/witcheer/8gb-vram-local-llms-practitioner-tested
>>> previous finding: Qwen3.6-35B-A3B via full expert offload on RTX 4060 Ti 8GB + 32GB RAM → 7.4 tok/sec. RAM-ceilinged, disk-bound.
>>> new finding: built llama.cpp from source inside WSL2, swept -ncmoe values for partial offload.
ncmoe 32, 16K ctx → 29.7 tok/sec
ncmoe 30, 16K ctx → 32.0 tok/sec
ncmoe 30, 32K ctx → 35.4 tok/sec
ncmoe 28, 16K ctx → 16.3 tok/sec (VRAM cliff)
ncmoe 30, 65K ctx → 17.4 tok/sec (VRAM cliff)4.8x faster than full offload. 8GB VRAM cliff is sharp - crossing ~7 GB halves throughput instantly.
the hybrid SSM+attention architecture means 32K context is nearly free (KV cache only scales for 10/40 layers).
dataset: witcheer/windows-rtx-4060ti-8gb-moe-offload-bench-2026-05
collection: https://hf.co/collections/witcheer/8gb-vram-local-llms-practitioner-tested
- 1 reply