niche · -1.1 capability schema

Coding Agents

Score 18.5 / 100 41 providers +8 via APIs 13 APIs Search apis.io →
Variants seen in the corpus: Coding AgentCoding Agents

Providers using this tag (41)

Ranked by API Evangelist rating — Exemplar and Strong are expanded by default.

Exemplar 2 Complete, well-documented, and agent-ready
Strong 5 Solid coverage with minor gaps
Developing 9 Usable, with meaningful gaps to close
Thin 9 Limited public surface area
Emerging 12 Early or largely undocumented
Minimal 4 Almost no public developer surface

APIs with this tag (13)

Ranked by the provider's API Evangelist rating — the Kin Score is scored per provider, not per API, so every API of a provider shares its band. How the rating works →

Exemplar 1 Complete, well-documented, and agent-ready
Strong 1 Solid coverage with minor gaps
Developing 5 Usable, with meaningful gaps to close
Thin 3 Limited public surface area
Emerging 3 Early or largely undocumented

Companies reaching this through an API (8)

These companies publish an API, specification or operation carrying “Coding Agents” but do not classify their business under it. Listed unranked and kept out of the count above, because one tagged operation is not a statement about what a company does.

Agentic AI Foundation Blacksmith LangWatch Letta OpenAI Publicis Groupe Waxell Чип (Chip AI)

Score breakdown

Frequency
44.1
log-scaled weighted occurrences
Breadth
0.5
spread across providers
Quality lift
34.2
mean composite of providers using it
Cohesion
3.4
strength of nearest seed neighbor

Where this tag sits

Developer Tools broader

Related tags

Pull Requests 5 co-occurrences Sandbox 6 co-occurrences CLI 9 co-occurrences Developer Tools 37 co-occurrences DevOps 9 co-occurrences APIKeys 6 co-occurrences Models 5 co-occurrences AI Agents 20 co-occurrences

Where this tag comes from

Api tag13
Provider tag41
Openapi tag1
Openapi op tag3

Cohort brief

Auto-generated

The 39 providers in the APIs.io catalog tagged Coding Agents, scored on the Kin Score. Every figure below is computed from the catalog — nothing here is written.

Providers
39
of 41 in the catalog
Mean Kin Score
35
+10.9 vs catalog 24.1
Mean Agent Readiness
19.3
+5.2 vs catalog 14.1
Spread
3–74
median 34.2 · σ 18.2
How the 39 split by band
Exemplar 2Strong 5Developing 9Thin 8Emerging 12Minimal 3
Facet averages, against the whole catalog
FacetThis cohortCatalogDifferenceScored
Developer Ergonomics 47 24.5 +22.5 39
Access Clarity 42.4 30 +12.4 39
Operational Transparency 24.7 13.2 +11.5 39
Discoverability 64.4 59.1 +5.3 39
Contract Quality 21.5 18.6 +2.9 39
Contract Governance 11.4 9.7 +1.7 39

A facet is averaged over the members that carry it, not over the whole cohort — the “Scored” column is that count. Averaging an absent facet as zero would score our own coverage gaps as the providers’ posture.

What this cohort publishes
ArtifactThis cohortCatalogDifference
MCP server (any) 44% 18% +26
MCP server (first-party) 49% 16% +33
Agent Skills 0% 0% 0
OAuth scopes 18% 13% +5
Security 100% 99% +1
Arazzo workflows 8% 1% +7
Governance rules 38% 36% +2

mcp_pct counts any mcp/ artifact including ones API Evangelist derived from the provider OpenAPI; mcp_first_party_pct counts only servers the provider publishes. Prefer the latter.

Top by Kin Score
  1. 1 GitHub Copilot 74
  2. 2 Tembo 71.7
  3. 3 Replicas 59.8
  4. 4 Amika 58.9
  5. 5 Runloop 57.5
  6. 6 ctlsurf 56.6
  7. 7 Relace 55.5
  8. 8 Coordigent 53.9
  9. 9 Standard Compute 50.6
  10. 10 Anysphere 49.8
Top by Agent Readiness
  1. 1 GitHub Copilot 53.2
  2. 2 Coordigent 52.9
  3. 3 Tembo 51.2
  4. 4 Hoplite 47.8
  5. 5 Replicas 39.3
  6. 6 Relace 38.8
  7. 7 Faylee 38.8
  8. 8 Kimetsu 34.7
  9. 9 ctlsurf 33
  10. 10 Scott Ai 32.6
All 41 members of this roster resolve to a provider in the catalog; 39 carry a score (95%). The figures above describe the scored members only.
Coverage caveat. 31 of 39 scored members had under half their catalog-attributable points satisfied at all (catalog_earned / catalog_max < 0.5). They are INCLUDED in the mean above. A large share here means the cohort mean is partly a measurement of how far our enrichment reached, not only of how these providers publish.Generated from the catalog build of 14 November 2026, across 41591 providers, using the same computation served by the APIs.io cohort API. Briefs are published for rosters of 5 or more scored providers; below that a distribution is not meaningful.

Work with this as data

Every tag here is available over the APIs.io API and to AI agents over MCP.

MCP server

One button, every client — Claude, Cursor, VS Code and the rest.

https://apis.io/mcp

Tools for tags

7 MCP tools reach this
  • find_tagsBrowse and filter every tag in the catalog.
  • get_cohortThis tag as a scored cohort — every provider carrying it, with scores.
  • cohort_statsPRO — the distribution across this tag: mean, median, band split, adoption rates.
  • cohort_rankingsPRO — the leaderboard, on composite AND agent-readiness axes.
  • apis_io_searchSTART HERE — APIs, providers and tags for one query, each with its total.
  • resolveTurn a domain, URL or GitHub org into the provider it belongs to.
  • find_cohortsEvery scored population of providers in the catalog.
All 92 tools →

Call it yourself

curl for this page
This tag
curl "https://apis.io/api/v1/tags/coding-agents"
All tags
curl "https://apis.io/api/v1/tags?limit=25"
As a scored cohort (paid plan)
The distribution (Pro)

Calls without X-API-Key need no key. Calls with it need a paid plan — get a key.

Get an API key

Free tier, no form to fill in. Signing in shares your email address with us — we store it to create your key and to recognise you if you sign in with another provider. See our Privacy Policy and Terms.

A second provider on the same verified email joins the account you already have.