Seth/gemma4-research
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

docs: add CLI coding agent research doc

Browse Source 
Fills the gap between existing chat-agent (Simon) and pipeline
(AI_Visualizer) patterns. Covers openclaw/open code/pi/hermes first-party
agents from the HF launch blog, honest positioning vs qwen3-coder:30b,
CLI-agent-specific gotchas (safety filter on security code, long-JSON
weakness, no code exec), and a concrete homelab bakeoff plan pointed at
CT 166 openclaw2 → CT 105 Ollama on pve197.

Key research finding: Google published LiveCodeBench + Codeforces but
NOT SWE-bench or Aider polyglot. The "autonomous agents" claim is
plausible but unproven for multi-file repo-scale coding specifically.
This commit is contained in:
Mortdecai
2026-04-18 13:01:59 -04:00
parent 5775978899
commit 4b9c537dda
3 changed files with 193 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files
SYNTHESIS.md
+1
View File
@@ -176,6 +176,7 @@ Vision is on ALL Gemma 4 variants (E2B, E4B, 26B, 31B). Audio is E-series only.
| Maximum quality (single-model GPU) | `gemma4:31b-it-q4_K_M` | Dense 31B, sharpest but 5x slower, more VRAM pressure |
| Rapid prototyping / testing | `gemma4:26b` | Fast enough for interactive dev |
| Retrieval / embeddings | `embeddinggemma` (308M, separate model) | Gemma 4 has no embedding mode; use the sibling |
| CLI coding agent (openclaw / open code / pi / hermes / aider) | `gemma4:26b` (or compare to `qwen3-coder:30b`) | Trained tool use + strong LiveCodeBench, but Google didn't publish SWE-bench — see `CORPUS_cli_coding_agent.md` for the honest positioning and the homelab bakeoff plan |
## Anti-Patterns