codehamrvsNeo
Generated from the two spec rows. Green marks the better value where a spec has a clear direction. Everything else is just different.
codehamr
codehamr · Terminal agent
#115OSS
Panel
6.72 spec wins
- Reliability
- 6.3
- Usefulness
- 5.8
- Cost
- 9.3
- Longevity
- 5.2
“Four tools and three slash commands, which is fewer features than most agents put in the onboarding screen.”
Neo
owainlewis · Terminal agent
#38OSS
Panel
6.73 spec wins
- Reliability
- 6.5
- Usefulness
- 6.3
- Cost
- 8.2
- Longevity
- 5.8
“You can queue your next instruction while it works, so now you can interrupt yourself without waiting for it to finish.”
Spec by spec
| Spec | codehamr | Neo |
|---|---|---|
| Architecture | ||
| Category | Terminal agent | Terminal agent |
| Runs | local | local |
| Platforms | macos, linux, windows | macos, linux |
| Context window | not documented | not documented |
| Protocols | ||
| MCP client | No | No |
| MCP server | No | No |
| Capabilities | ||
| Runs terminal commands | Yes | Yes |
| Multi-file edits | Yes | Yes |
| Git operations | No | Yes |
| Browser control | NoThe agent can bootstrap a headless browser as a verification helper when the machine allows it, but it has no browser tool of its own. | No |
| Sandboxed execution | No | YesNeo describes sandbox-first execution where the runtime contains tools; the README does not specify a container technology. |
| Multi-agent orchestration | No | Yes |
| Headless / CI mode | No | No |
| Models | ||
| Backbone | Ollama, vLLM, LM Studio, OpenAI-compatible endpoints | Anthropic, OpenAI, Google Gemini, OpenRouter |
| Bring your own model | Yes | Yes |
| Local models | Yes | No |
| Cost | ||
| Pricing model | byok | byok |
| Starts at | $0/mo | $0/mo |
| Free tier | Yes | Yes |
| Bring your own key | Yes | Yes |
| Openness | ||
| Open source | Yes | Yes |
| License | MIT | MIT |
| GitHub stars | 219 | 145 |
Which one would each critic pick
| Critic | codehamr | Neo | Pick |
|---|---|---|---|
| El Juez | — | — | not enough reviews |
| El Amigo | 6.8 | 7.3 | Neo — Pick this if you lose the thread inside chat transcripts; pick a conversational agent if you would rather talk to it than read a dashboard of what it is doing. |
| El Crítico | 6.3 | 6.8 | Neo — Execution is called sandbox-first and the documentation names no containment technology, while confirmation is optional and applies only to selected interactive calls. |
| El Profesor | 7.8 | 7.5 | codehamr — It runs the tests, compiles, or loads the page, and prints `unverified:` when it cannot, which is the rarest honesty in this category. |
| La Inversora | 6.0 | 6.0 | no preference |
| La Jefa | 5.8 | 5.8 | no preference |
| El Hacker | 7.5 | 7.0 | codehamr — MIT, a `local` profile for Ollama, vLLM and LM Studio, and any OpenAI-compatible endpoint, so the whole loop runs on hardware I built. |
Picks are derived from each critic's own scores. Humans vote on matchups on the duels page.