Agents Built on Jev, Compared
Jev is TypeSafe AI's System One model, released in September 2026, and these are the reviewed agents in the catalogue that use it: coding-agent harnesses, MCP servers, permission gates, browser automation and more. Most are days or weeks old, so expect small star counts, and read the FARS confidence next to each score. New arrivals are picked up automatically. If you are new to Jev itself, start with the topic guide.
New to Jev? Read the topic guide →
| # | Agent | FARS | Trust | Stars | Stars/day (7d) | Latest release | License | Language | Last commit |
|---|---|---|---|---|---|---|---|---|---|
| 1 | Web Search Plus for Hermes | 92 | 25/29 | 440 | +0.1 | v5.1.72026-10-31 |
MIT | Python | 2026-10-31 |
| 2 | jev-axi Judgment CLI | 90 | 23/29 | 47 | +0.3 | v0.7.32026-10-24 |
MIT | TypeScript | 2026-10-24 |
| 3 | Jev Review | 81 | 23/29 | 247 | -0.3 | — | MIT | TypeScript | 2026-09-17 |
| 4 | Pi Jev Semantic Router | 80 | 19/29 | 72 | +0.4 | v0.8.02026-10-29 |
MIT | TypeScript | 2026-10-29 |
| 5 | Jev Guard | 79 | 19/29 | 145 | +1.9 | v0.3.12026-09-17 |
MIT | JavaScript | 2026-10-02 |
| 6 | lcc — Local Context Compiler | 78 | 21/29 | 17 | +0.2 | v1.3.02026-10-31 |
MIT | Python | 2026-11-04 |
| 7 | Supercov | 75 | 16/29 | 159 | +0.1 | v4.24.02026-11-05 |
MIT | Rust | 2026-11-05 |
| 8 | Jev Browser | 75 | 16/29 | 129 | +0.4 | v0.2.12026-10-17 |
MIT | JavaScript | 2026-10-31 |
| 9 | Pi Jev Auto Mode | 73 | 18/29 | 33 | 0.0 | v0.6.02026-10-18 |
MIT | TypeScript | 2026-10-18 |
| 10 | Jev Social | 71 | 17/29 | 198 | +1.1 | v0.1.132026-09-29 |
MIT | JavaScript | 2026-11-01 |
| 11 | TypeSafe Evaluate | 70 | 16/29 | 358 | +0.4 | v0.4.142026-11-03 |
MIT | Go | 2026-11-03 |
| 12 | Jevbridge Decision Sidecar | 62 | 14/29 | 48 | +0.1 | — | MIT | TypeScript | 2026-09-21 |
The order is the FARS total; stars only break ties, because popularity measures attention rather than whether something holds up. Two limits are worth knowing before you read the order. These are static reviews — source, documentation and repository metadata, with no runtime reproduction — which caps reliability, effectiveness and verifiability and puts the achievable maximum at 77 rather than 100. And a gap of a few points sits inside the noise of that method. Read the table as a shortlist worth investigating, not as a verdict; every score links to its full dimension breakdown and the evidence behind it. Review method →
1. Web Search Plus for Hermes
Give Hermes multi-provider web search and clean extraction backed by real source links.
Where it differs
Compared with Hermes' native web_search and web_extract, Web Search Plus adds a multi-provider engine, fallback, caching, and quality reporting. Its optional wsp backend can route those native calls through the WSP engine, but merely installing the plugin does not select that backend. The repository also identifies web-search-plus-plugin as the TypeScript/OpenClaw edition, whereas this repository is the Python port for the Hermes Agent plugin API. DonSeTch is not a bundled substitute: it is an independent AGPL-3.0-only local MCP program connected through a separate stdio process.
2. jev-axi Judgment CLI
Fast probabilistic safety and workflow judgments for coding agents, shell commands, diffs, logs, and untrusted text.
Where it differs
Unlike foreman, which runs Jev as a supervisor above a coding agent, jev-axi does not launch the agent; it connects similar completion and progress judgments to the agent's existing hooks. It also differs from generative coding models: Jev returns typed probabilistic judgments and never writes prose, so jev-axi complements rather than replaces code generation and code comprehension.
3. Jev Review
Continuous, structured software-quality scoring for AI coding agents.
4. Pi Jev Semantic Router
Routes Pi tools, discovers skills, selects models, and makes fast typed decisions on demand.
Where it differs
Compared with Pi's normal compaction, Jev-guided compaction evaluates tool-history entries to retain important paths, errors, constraints, and results; it falls back to Pi's built-in summary when Jev is unavailable, unconfigured, or returns unusable data. For rapid workflow classification, agent: "jev" is positioned as a typed decision node that avoids spawning a heavyweight LLM process, rather than as a full execution subagent.
5. Jev Guard
Risk-score every coding-agent tool call and stop dangerous actions or prompt-injected instructions.
Where it differs
Claude Code auto mode uses a separate classifier model to review actions. Jev Guard implements a comparable allow, ask, and deny flow through typed Jev questions such as risk, user_requested, and from_untrusted. Its distinguishing scope is the same policy across Codex, Copilot CLI, Gemini CLI, Cursor, pi, OpenCode, and ACP, while also serving as a second opinion inside Claude Code. The tradeoff is dependence on the external Jev service and weaker ask behavior on hosts whose hook APIs cannot request approval.
6. lcc — Local Context Compiler
Shrinks coding-agent context without summarizing it away: byte-exact spans, offline judging, and a recall path for every cut.
Where it differs
The README positions lcc mainly against Claude Code's built-in /compact: /compact replaces the session with a model-written summary that drops the exact error, path or line the agent needs two turns later, whereas lcc keeps every user and assistant message and only moves old tool outputs out of context, one recall away. The benchmark section also compares rankers against recency, bm25 and random baselines using retention AUC.
7. Supercov
Give coding agents verifiable quality scores and precise coverage gaps to fix one useful target at a time.
Where it differs
Compared with coverage workflows that make an agent load a large HTML report, Supercov exposes small, paginated gaps queries and verifies gains through diff. Compared with hosted coverage services, its coverage execution stays under the local .supercov/ directory and does not contact a Supercov service; quality scoring is separate and does depend on TypeSafe AI's Jev API. It is also neither a test runner nor an agent platform: it wraps an existing test command and supplies quality and coverage evidence.
8. Jev Browser
Browser automation in which an LLM sets the goal, Jev chooses the action, and Playwright executes it.
Where it differs
The repository estimates context usage against a Playwright-MCP-style snapshot loop on the same tasks. It reports roughly five times less context per task at the median and about 8,000 versus 557,000 tokens overall, because page reading moves to Jev. Large pages account for much of that difference, while tiny pages show no saving. The source does not provide a comprehensive comparison of success rate, monetary cost, or total feature coverage.
9. Pi Jev Auto Mode
A fail-closed permission gate for Pi shell commands and file changes.
Where it differs
Its deterministic pattern catalogue is adapted from @nilskluewer/pi-auto-permission-gate, and the README relates its fast-path → hard-rule → classifier structure to both that extension and Qwen Code's Auto Mode. The documented distinction is the TypeSafe Jev judgment layer, combined with fail-closed outcomes, meaningful two-sided thresholds, one API request per judgment, and recorded per-condition probabilities.
10. Jev Social
Research Instagram, TikTok, and LinkedIn through Jev-directed operations in a real browser.
Where it differs
Compared with calling socai directly, Jev Social adds a per-observation decision loop in which Jev selects the next operation from changing candidates and compiles cards, tables, and an evidence report. Direct socai commands are the simpler option when the platform and exact operation are already known. Jev Social explicitly does not hand browsing to another research agent or depend on socai research.
11. TypeSafe Evaluate
Give agents typed judgments and probabilities they can branch on instead of prose they must parse.
Where it differs
Compared with asking a general LLM for prose and parsing the result, evaluate returns typed JSON with probabilities, removing prompt-format maintenance and fragile text extraction. TypeSafe API and OpenRouter Decisions are alternative request routes, but both use Jev; when both credentials are configured, TYPESAFE_API_KEY wins.
12. Jevbridge Decision Sidecar
Add typed decisions, confidence gates, and computer-use action selection to an existing LLM.
Where it differs
Compared with asking a generative LLM to produce prose and make every operational decision, Jevbridge constrains decisions to noul, choice, and score outputs and applies a separate confidence gate. Native TypeSafe Jev is the preferred backend, while Codex, Claude, Grok, OpenCode, or a generic OpenAI-compatible model can provide the System One role without a TypeSafe key. The heuristic backend works offline but is intended only for tests, not as a substitute for safety-sensitive model decisions.