CoreCodervsViden
Generated from the two spec rows. Green marks the better value where a spec has a clear direction. Everything else is just different.
CoreCoder
He Yufeng · Terminal agent
#215OSS
Panel
5.92 spec wins
- Reliability
- 5.5
- Usefulness
- 5.2
- Cost
- 7.8
- Longevity
- 5.0
“It ships eight essays explaining its own source code, which is eight more than most agents ship.”
Viden
wikieden · Terminal agent
#212OSS
Panel
5.92 spec wins
- Reliability
- 5.7
- Usefulness
- 5.5
- Cost
- 7.5
- Longevity
- 4.8
“The cockpit displays provider health, so you can watch in real time the outage that is ruining your afternoon.”
Spec by spec
| Spec | CoreCoder | Viden |
|---|---|---|
| Architecture | ||
| Category | Terminal agent | Terminal agent |
| Runs | local | local |
| Platforms | macos, linux, windows | macos, linux, windows |
| 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 | No | YesViden ships a web tool in its shared runtime path; it is not a full browser- automation agent. |
| Sandboxed execution | No | No |
| Multi-agent orchestration | Yes | Yes |
| Headless / CI mode | Yes`corecoder -p` runs a single prompt non-interactively, but the tool guard is a regex blacklist, not a security sandbox. | No |
| Models | ||
| Backbone | any OpenAI-compatible endpoint, Ollama, LiteLLM | DeepSeek, OpenAI, Anthropic, Ollama |
| Bring your own model | Yes | Yes |
| Local models | YesDocumented with a local Ollama endpoint via OPENAI_BASE_URL, and an optional LiteLLM backend for other providers. | Yes |
| 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 | 1,788 | 87 |
Which one would each critic pick
| Critic | CoreCoder | Viden | Pick |
|---|---|---|---|
| El Juez | — | — | not enough reviews |
| El Amigo | 6.0 | 6.3 | Viden — Pick it if you want one screen showing what the agent is doing and what is broken; pick a plain chat agent if you never wanted a dashboard in the first place. |
| El Crítico | 5.5 | 5.5 | no preference |
| El Profesor | 7.0 | 6.5 | CoreCoder — 1,217 lines cover the loop, model interface, context, tools and sessions, with three-tier compaction and a per-run token and cost report; the protocol layer is deliberately absent. |
| La Inversora | 4.3 | 4.3 | no preference |
| La Jefa | 4.3 | 5.5 | Viden — Transcripts, task events and artifacts are stored locally by default, which answers where the data lives and leaves me with sixty copies of it. |
| El Hacker | 8.3 | 7.3 | CoreCoder — MIT, one pip command, and a base URL environment variable pointed at my own server, with an optional router underneath for everything else. |
Picks are derived from each critic's own scores. Humans vote on matchups on the duels page.