Agentic Index
Potpie AI vs Sourcegraph (2026)
Both vendors last verified
Sourcegraph and Potpie both make enormous codebases legible to humans and agents. That verdict is the Agentic Index coverage score, graded from each vendor's own published materials.
Sourcegraph is the enterprise incumbent, with exhaustive code search, Batch Changes across hundreds of repositories, and a code graph feeding agents over MCP, with SOC 2 and ISO 27001. Potpie is the open source challenger, an ontology first knowledge graph with prebuilt debugging and review agents, young but distinctive.
On the Agentic Index coding agent ranking, neither Potpie AI nor Sourcegraph clears the bar, which asks for all five merge loop capabilities documented in full. Potpie AI documents two of the five in full; Sourcegraph does not document testing, debugging and optimization in full. 3 of the 96 vendors in the lane clear it. See the coding agent ranking
This comparison is published by Agentic Index, an independent agentic AI vendor research platform. Potpie AI and Sourcegraph are each graded against the same 14 capability Agentic Index taxonomy, from the vendor's own public materials under the Agentic Index verification standard, alongside 1,165 researched vendors. No vendor pays for placement and no vendor has reviewed this page. How this evidence is graded
Choose Potpie AI if
- You want the graph and agents open source under Apache, self hosted with your own model keys.
- Root cause analysis and blast radius detection on million line systems is the immediate job.
- Installing context skills into Claude Code, Codex, and Cursor upgrades tools you already run.
Choose Sourcegraph if
- Enterprise scale and certifications matter, with SOC 2, ISO 27001, air gapped options, and a decade of hardening.
- Batch Changes rolling one fix across hundreds of repositories is the feature you keep needing.
- You want a proven vendor for Big Code rather than a pre seed startup.
| Feature | P Potpie AI |
S Sourcegraph |
|---|---|---|
| Action & orchestration | ||
|
Integrations & Tool Calling Ability to connect agents to real systems through native integrations, OAuth-authenticated actions, custom tools, APIs, webhooks, or MCP-compatible tools. |
||
|
Potpie AIIntegrations & Tool Calling There are four integrations across source control, ticketing and documentation. GitHub covers repositories, pull requests, issues, reviews and source history, Linear covers teams, issues, projects and documents, Jira covers projects, issues, status and changelog context, and Confluence covers spaces, pages, runbooks and decisions, each connected through CLI auth commands with credential verification via potpie auth status --verify. Potpie also installs its instructions and skills into four coding harnesses, Claude Code, OpenAI Codex, Cursor and OpenCode, so those agents call it for context. There is no Notion, Slack or VS Code extension integration. Sourcegithub.com/potpie-ai/potpieread 2026-08-30 |
||
|
SourcegraphIntegrations & Tool Calling Changesets go out to each code host through Agentic Batch Changes, which runs CI across GitHub, GitLab and Bitbucket and tracks each pull request through to merge, and the platform indexes all major code hosts. The MCP server works the other way, exposing Sourcegraph's own code graph to agents such as Claude Code, Cursor, Codex and Amp. Sourcesourcegraph.com/agentic-batch-changesread 2026-09-29 |
||
|
Workflow Orchestration Ability to sequence, branch, retry, route, and combine deterministic workflow nodes with autonomous agent steps. |
||
|
Potpie AIWorkflow Orchestration Potpie either operates as a single agent or delegates execution to specialized subagents, and customers define custom agents by role, goal, backstory and system prompt with tasks, tools and expected outputs, so it supports both runs across several agents and a flow the customer configures. Sourcedocs.potpie.ai/custom-agents/introductionread 2026-09-29 |
||
|
SourcegraphWorkflow Orchestration Agentic Batch Changes, now generally available, runs a coordinator agent that takes a plain-language change and scopes it across the indexed codebase with Deep Search. It splits the work by code ownership and routes each repository to a deterministic script or a delegated coding agent, in isolated containers running in parallel, then publishes changesets, reads CI logs and patches failures until CI is green. Sourcesourcegraph.com/agentic-batch-changesread 2026-09-29 |
||
|
Triggers & Channel Coverage How agents wake up and where they work: schedules, webhooks, message events, CRM events, inbox events, chat, email, voice, and collaboration tools. |
||
|
Potpie AITriggers & Channel Coverage Recipe, an enterprise workflow layer, runs durable workflows on cron or calendar schedules and on repository changes, incident alerts and deployment events, so work starts without a person invoking it. The open source CLI is invoked by hand or from inside Claude Code, Codex, Cursor and OpenCode. Sourcedocs.potpie.ai/build-flow/reciperead 2026-10-25 |
||
|
SourcegraphTriggers & Channel Coverage Code Monitoring alerts agents and teams the moment code changes, and Agentic Batch Changes uses changeset hooks for CI so the agent reacts to CI results and iterates without being prompted. Both start work when an event occurs. The web app, IDE extensions, CLI and MCP server are used on demand. Sourcesourcegraph.comread 2026-09-29 |
||
| Knowledge & context | ||
|
Knowledge Grounding & RAG Ability to ground agent behavior in company data through document ingestion, retrieval, external knowledge APIs, semantic search, or RAG layers. |
||
|
Potpie AIKnowledge Grounding & RAG The repository is parsed into a property graph capturing every file, function, class, import and call relationship, held in a graph database, then layered with source history, decisions, tickets and team knowledge so agents can perform multi-hop reasoning across components. Integrations index GitHub repositories, pull requests, issues, reviews and source history, Linear teams, issues, projects and documents, Jira projects, issues, status and changelog context, and Confluence spaces, pages, runbooks and decisions. The CLI exposes potpie resolve to pull the context an agent should read before a task and potpie search to look up a specific file, workflow, bug, decision or convention, and Potpie reports operation on codebases from roughly one million to hundreds of millions of lines. Sourcedocs.potpie.ai/introduction and github.com/potpie-ai/potpieread 2026-08-30 |
||
|
SourcegraphKnowledge Grounding & RAG The code graph indexes every repository, branch and code host across an organization, mapping relationships between symbols, references and definitions for exhaustive exact search at monorepo and multi repository scale. Deep Search runs an agent that explores repositories autonomously and returns grounded answers with citations, Cody Enterprise retrieves relevant code from up to ten repositories simultaneously, and an MCP server feeds that complete indexed context to third party agents. Sourcesourcegraph.com and sourcegraph.com/docsread 2026-08-30 |
||
|
Memory & State Persistence Ability to persist context across a run, conversation, workflow, user, team, or longer-term memory layer. |
||
|
Potpie AIMemory & State Persistence The Context Engine includes a graph-backed memory layer for entities, claims, source refs and timelines. Agents propose memory through semantic mutation, the record tool saves durable project memory such as decisions, observations and validated graph facts, and resolve and search read it back, all scoped to one pot. The memory has a stated scope and a durable lifetime, and deletion is not addressed. It is separate from the code graph that grounds knowledge. Sourcedocs.potpie.ai/concepts/context-engineread 2026-09-29 |
||
|
SourcegraphMemory & State Persistence Agentic Batch Changes keeps run state across a migration, including which repositories are in scope, which changesets have landed and pull request sync, and follows customizable skills and AGENTS.md set per user, org or globally. The skills are instructions the customer writes and the code graph is a search index, so what persists is run state, with no stated scope, lifetime or review. Sourcesourcegraph.com/agentic-batch-changesread 2026-09-29 |
||
| Control & trust | ||
|
Human Oversight & Guardrails Approval steps, consent checkpoints, escalation rules, structured guardrails, policy constraints, and pause/resume controls. |
||
|
Potpie AIHuman Oversight & Guardrails Spec-driven development is the main workflow, putting upfront planning first to define clear requirements and architecture before code is written, so the plan is reviewable ahead of implementation. The CLI surfaces context for review through potpie resolve before a task begins, the graph explorer makes the context inspectable, and potpie graph exposes proposals and commits as distinct operations. There is no per-action approval gate, tool permission scoping or configurable runtime guardrail, and because Potpie supplies context rather than executing changes itself, enforcement of any write path rests with the configured coding harness. Sourcedocs.potpie.ai/introduction and github.com/potpie-ai/potpieread 2026-08-30 |
||
|
SourcegraphHuman Oversight & Guardrails Agentic Batch Changes researches, plans and revises freely without publishing anything. The first run usually takes an explicit yes. Publishing and rollout can each wait on a person's reply unless they were authorized up front, and steps that use secrets wait for approval. Teams validate a change on a few repositories before rolling it out. Sourcesourcegraph.com/docs/agentic-batch-changes/configurationread 2026-10-25 |
||
|
Security, Identity & Governance RBAC, SSO, auditability, encryption, least-privilege tool access, compliance posture, and data handling policy. |
||
|
Potpie AISecurity, Identity & Governance The trust center at trust.potpie.ai lists SOC 2 Type II, ISO 27001:2022 and ISO 42001:2023, with an on premises option and Google Cloud hosting. SSO, SAML, SCIM and role based access are not documented. Sourcetrust.potpie.ai and docs.potpie.airead 2026-10-25 |
||
|
SourcegraphSecurity, Identity & Governance Sourcegraph states SOC 2 Type II and ISO 27001 compliance and offers enterprise authentication with SSO through SAML, OpenID Connect and OAuth, SCIM provisioning and lifecycle management, and RBAC. Authentication can be configured through SAML, OAuth, HTTP proxy and OpenID Connect, annual third-party penetration tests are run, and LLM inference data has zero retention. Sourcesourcegraph.comread 2026-09-29 |
||
|
Observability & Auditability Traces, logs, execution histories, metrics, audit events, and debugging detail for production agent behavior. |
||
|
Potpie AIObservability & Auditability The CLI reports on the context layer (status, doctor, auth checks, graph reads), and a local graph explorer makes the context inspectable. The homepage states that every run is logged with agent, action, tokens and outcome in an agent activity log. The documentation does not describe that log, how long it is kept or how to export it. Sourcepotpie.ai, potpie.ai/llms.txt and github.com/potpie-ai/potpieread 2026-10-25 |
||
|
SourcegraphObservability & Auditability The Agentic Batch Changes console records the coordinator's run step by step, covering scoping, container launch per repository, changeset publication per code host and each CI failure read and patched. It shows per-repository execution status, per-changeset PR tracking in the web UI and coverage tracking of which repositories have landed, and Batch Changes execution keeps executor and pull request sync state. No retention period or export for run records is published. Sourcesourcegraph.com/agentic-batch-changesread 2026-09-29 |
||
|
Deployment & Data Residency Deployment modes and options, including SaaS, dedicated cloud, VPC, on-prem, hybrid, local runtime, and self-hosting. |
||
|
Potpie AIDeployment & Data Residency The platform is published under Apache 2.0 with a CLI-first architecture installed from PyPI, where the setup wizard provisions local config, local storage, a local daemon and a default pot, and potpie ui serves a graph explorer from that local daemon in the developer's browser. The whole platform can be self-hosted, and account-backed managed features are opt-in through potpie login rather than required. The repository includes architecture notes for self-deployment, and Potpie reports deployments in regulated industries including healthcare and insurance technology. Sourcegithub.com/potpie-ai/potpieread 2026-08-30 |
||
|
SourcegraphDeployment & Data Residency Deployment spans Sourcegraph Cloud, customer self hosted instances and fully air gapped environments for the largest monorepo and multi repository architectures. LLM inference data is kept out of retention, and Cody supports cloud hosted or self hosted model endpoints including Azure OpenAI, AWS Bedrock and OpenAI compatible gateways. Sourcesourcegraph.com and sourcegraph.com/docs/admin/deployread 2026-08-30 |
||
| Solution readiness | ||
|
Prebuilt Agents, Templates & Packs Ready-made workflows, packaged employees, templates, blueprints, industry solutions, and role-specific agents that reduce time-to-value. |
||
|
Potpie AIPrebuilt Agents, Templates & Packs Named prebuilt agents each do their own job and are callable through the API, namely a codebase Q&A agent, a code generation agent, a spec generation agent and a debugging agent, beside skills installed into Claude Code, Codex, Cursor and OpenCode. Sourcedocs.potpie.ai/agents/api-accessread 2026-09-29 |
||
|
SourcegraphPrebuilt Agents, Templates & Packs Batch Changes are defined by reusable declarative specification files that can be templated, versioned and shared for recurring cross repository migrations, with published example specs, and saved searches and code monitors are reusable configuration. There is no catalog of installable prebuilt agents, skills or packs. Sourcesourcegraph.com/docs/batch-changes and sourcegraph.comread 2026-08-30 |
||
| Platform extensibility | ||
|
Model Flexibility & Routing Ability to work across multiple foundation models, route tasks to different models, or let buyers bring their own providers and keys. |
||
|
Potpie AIModel Flexibility & Routing Self hosters set the provider and models themselves through environment variables (LLM_PROVIDER, CHAT_MODEL, INFERENCE_MODEL), with a local Ollama model given as the worked example, so the customer chooses the model. Sourcedocs.potpie.ai/self-hosting/setupread 2026-09-29 |
||
|
SourcegraphModel Flexibility & Routing Cody's supported models include chat and prompt models from Anthropic (Claude Opus and Sonnet 5 line, Haiku 4.5), Google (Gemini 3.x Flash and Pro) and OpenAI (GPT-6), which site admins configure through modelConfiguration and users select per use case, alongside customer chosen endpoints on Azure OpenAI, AWS Bedrock and OpenAI compatible gateways. Cody is no longer listed on the pricing page, though its model reference is current. Sourcesourcegraph.com/docs/cody/capabilities/supported-modelsread 2026-09-29 |
||
|
APIs, SDKs & MCP Extensibility Composability layer: stable APIs, SDKs, MCP tool consumption/serving, custom tools, and integration into internal systems. |
||
|
Potpie AIAPIs, SDKs & MCP Extensibility An API (x-api-key header, /api/v2 on the Potpie server) parses a repository, creates a conversation bound to an agent and sends messages with streaming and citations, beside the PyPI CLI driven by people and agents and the Apache 2.0 source. Sourcedocs.potpie.ai/agents/api-accessread 2026-09-29 |
||
|
SourcegraphAPIs, SDKs & MCP Extensibility An MCP server is a shipped product exposing the code graph to third party agents, alongside public APIs that drive code search and Batch Changes programmatically, a CLI, IDE extensions for VS Code, JetBrains and Visual Studio, and a browser extension. The SCIP Code Intelligence Protocol is fully open source, though the Sourcegraph and Cody source code moved to private repositories, with only a public snapshot remaining. Sourcesourcegraph.com, sourcegraph.com/docs and github.com/sourcegraph/scipread 2026-08-30 |
||
|
Testing, Debugging & Optimization Testing, debugging, scoring, retries, fallbacks, quality gates, and optimization loops for improving agent workflows before and after deployment. |
||
|
Potpie AITesting, Debugging & Optimization Debugging and root cause analysis are example uses of the context layer, with multi-hop reasoning across components, and one customer cut root cause analysis on a 40 million line codebase from nearly a week to 30 minutes. Tests are aligned against a plan before code is written through spec-driven development, and the CLI exposes graph quality checks. Potpie also open-sources SWE-bench predictions, execution logs, trajectories and evaluation results from its own benchmarking, and it publishes research on agent evaluation data. Customers get no evaluation, regression testing or debugging product for agent behavior. Sourcedocs.potpie.ai/introduction, github.com/potpie-ai and potpie.ai/blogread 2026-08-30 |
||
|
SourcegraphTesting, Debugging & Optimization Complete code graph context, Sourcegraph says, makes third party agents produce better results with fewer retries and lower inference cost. Code Insights track code health metrics over time, and Batch Changes previews validate a change set before it is applied. There is no customer facing harness for testing, evaluating or regression testing agent behavior. Sourcesourcegraph.com and sourcegraph.com/docsread 2026-08-30 |
||
| Specialist automation | ||
|
Browser & Computer Use Browser, desktop, or remote/local computer control for workflows that cannot be handled through stable APIs alone. |
||
|
Potpie AIBrowser & Computer Use All operation runs through programmatic interfaces, namely a Python CLI installed from PyPI, a local daemon serving a graph explorer, repository parsing into a graph database, integration APIs for GitHub, Linear, Jira and Confluence, and skill files installed into coding harnesses that those harnesses read. There is no browser control, screenshot capture, visual verification or way to operate software lacking a programmatic interface. Sourcegithub.com/potpie-ai/potpie and docs.potpie.ai/introductionread 2026-08-30 |
||
|
SourcegraphBrowser & Computer Use Sourcegraph operates on indexed repositories through its web application, IDE extensions, CLI and MCP server. A browser extension adds code search and navigation to code host pages, but it is a UI overlay for the user, not the agent operating software, and there is no browser control or computer use capability. Sourcesourcegraph.comread 2026-08-30 |
||
Pricing snapshot
Sourced from the Index pricing dataset · open each vendor's profile for full detail.
| Pricing | P Potpie AI |
S Sourcegraph |
|---|---|---|
|
Entry price Lowest public entry point |
Free and open source to self host (Apache 2.0). The commercial offer is an embedded engagement priced by the project, not per seat, through a demo. | Enterprise from $16K a year (minimum annual contract, AI credits included). Agentic Batch Changes is metered per user per repository run, and its model use draws on credits. |
|
Pricing confidence How public the numbers are |
Contact only | Public, partial |
|
Billing Primary billing axis |
Per project engagement, not per seat | Annual platform contract that scales with team size, with credits for AI features included per user and pooled across the organization. Agentic Batch Changes runs are metered per user per repository through an entitlement. |
|
Variable cost Workload / overage exposure |
Medium variable cost | Medium variable cost |
|
Free tier / trial Try before you buy |
Free tier
|
No free tier
|
|
Buying motion Self-serve vs sales call |
Sales call | Sales call |
|
Pricing verified When this pricing was last checked |
Product updates
Newest first, each linked to its source.
Sourcegraph
-
· Security / enterprise
Batch changes run by the Agentic Batch Changes agent are now applied and published as the user acting on them, and workspace execution jobs run as that user too.
Source -
· Workflow orchestration
Agentic Batch Changes no longer holds the conversation open while its workspaces run.
Source -
· MCP / tool calling / API
Connector support for Sourcegraph agents now extends to personal connectors, which each user adds from their own settings next to the shared ones admins set up.
Source
More comparisons with Potpie AI or Sourcegraph
Other matchups in coding agents
Not the pairing you were after? These compare a different set of coding agents on the same 14 capabilities.